# Running on cnode7-008 # Started at Tue Dec 10 08:38:43 CST 2024 # SLURMD_NODENAME=cnode7-008 # SLURM_CLUSTER_NAME=slurm # SLURM_CONF=/cm/shared/apps/slurm/var/etc/slurm/slurm.conf # SLURM_CPUS_ON_NODE=224 # SLURM_CPUS_PER_TASK=8 # SLURM_EXPORT_ENV=PATH # SLURM_GET_USER_ENV=1 # SLURM_GPUS_ON_NODE=8 # SLURM_GPUS_PER_NODE=8 # SLURM_GTIDS=0 # SLURM_JOBID=6577 # SLURM_JOB_CPUS_PER_NODE='224(x2)' # SLURM_JOB_END_TIME=1765327120 # SLURM_JOB_GID=1026 # SLURM_JOB_GPUS=0,1,2,3,4,5,6,7 # SLURM_JOB_ID=6577 # SLURM_JOB_NAME=exp_owsm/s2t_train_05b_ds_raw_bpe50000/train.log # SLURM_JOB_NODELIST='cnode7-[008-009]' # SLURM_JOB_NUM_NODES=2 # SLURM_JOB_PARTITION=p2 # SLURM_JOB_QOS=normal # SLURM_JOB_START_TIME=1733791120 # SLURM_JOB_UID=1026 # SLURM_JOB_USER=williamchen # SLURM_LOCALID=0 # SLURM_MEM_PER_NODE=2048000 # SLURM_NNODES=2 # SLURM_NODEID=0 # SLURM_NODELIST='cnode7-[008-009]' # SLURM_NODE_ALIASES='(null)' # SLURM_OPEN_MODE=a # SLURM_PRIO_PROCESS=0 # SLURM_PROCID=0 # SLURM_SUBMIT_DIR=/mnt/home/williamchen/espnet/egs2/owsm_v3.1/s2t1 # SLURM_SUBMIT_HOST=154-T2-P1-NVR # SLURM_TASKS_PER_NODE='28(x2)' # SLURM_TASK_PID=627117 # SLURM_TOPOLOGY_ADDR=cnode7-008 # SLURM_TOPOLOGY_ADDR_PATTERN=node # SLURM_WORKING_CLUSTER=slurm:154-T2-P1-NVR:6817:9984:109 # srun --export=ALL python3 -m espnet2.bin.s2t_train --use_preprocessor true --bpemodel data/token_list/bpe_unigram50000/bpe.model --token_type bpe --token_list data/token_list/bpe_unigram50000/tokens.txt --non_linguistic_symbols none --cleaner none --g2p none --valid_data_path_and_name_and_type dump/raw/dev_v3/wav.scp,speech,kaldi_ark --valid_shape_file exp_owsm/s2t_stats_raw_bpe50000/valid/speech_shape --resume true --fold_length 80000 --output_dir exp_owsm/s2t_train_05b_ds_raw_bpe50000 --config conf/train_05b_ds.yaml --frontend_conf fs=16k --normalize=global_mvn --normalize_conf stats_file=exp_owsm/s2t_stats_raw_bpe50000/train/feats_stats.npz --train_data_path_and_name_and_type exp_owsm/s2t_stats_raw_bpe50000/splits8/wav.scp,speech,kaldi_ark --train_shape_file exp_owsm/s2t_stats_raw_bpe50000/splits8/speech_shape --fold_length 150 --train_data_path_and_name_and_type exp_owsm/s2t_stats_raw_bpe50000/splits8/text.prev,text_prev,text --fold_length 150 --train_data_path_and_name_and_type exp_owsm/s2t_stats_raw_bpe50000/splits8/text.ctc,text_ctc,text --fold_length 150 --train_data_path_and_name_and_type exp_owsm/s2t_stats_raw_bpe50000/splits8/text,text,text --multiple_iterator true --valid_data_path_and_name_and_type dump/raw/dev_v3/text.prev,text_prev,text --valid_data_path_and_name_and_type dump/raw/dev_v3/text.ctc,text_ctc,text --valid_data_path_and_name_and_type dump/raw/dev_v3/text,text,text --ngpu 8 --multiprocessing_distributed true --dist_launcher slurm --dist_init_method file:///mnt/home/williamchen/espnet/egs2/owsm_v3.1/s2t1/exp_owsm/s2t_train_05b_ds_raw_bpe50000/.dist_init_ee66adec-3a3c-4487-9810-766b99137415 [2024-12-10 08:39:00,861] [INFO] [real_accelerator.py:219:get_accelerator] Setting ds_accelerator to cuda (auto detect) [2024-12-10 08:39:02,038] [INFO] [real_accelerator.py:219:get_accelerator] Setting ds_accelerator to cuda (auto detect) /mnt/home/williamchen/espnet/tools/miniconda/envs/espnet/bin/python3 /mnt/home/williamchen/espnet/espnet2/bin/s2t_train.py --use_preprocessor true --bpemodel data/token_list/bpe_unigram50000/bpe.model --token_type bpe --token_list data/token_list/bpe_unigram50000/tokens.txt --non_linguistic_symbols none --cleaner none --g2p none --valid_data_path_and_name_and_type dump/raw/dev_v3/wav.scp,speech,kaldi_ark --valid_shape_file exp_owsm/s2t_stats_raw_bpe50000/valid/speech_shape --resume true --fold_length 80000 --output_dir exp_owsm/s2t_train_05b_ds_raw_bpe50000 --config conf/train_05b_ds.yaml --frontend_conf fs=16k --normalize=global_mvn --normalize_conf stats_file=exp_owsm/s2t_stats_raw_bpe50000/train/feats_stats.npz --train_data_path_and_name_and_type exp_owsm/s2t_stats_raw_bpe50000/splits8/wav.scp,speech,kaldi_ark --train_shape_file exp_owsm/s2t_stats_raw_bpe50000/splits8/speech_shape --fold_length 150 --train_data_path_and_name_and_type exp_owsm/s2t_stats_raw_bpe50000/splits8/text.prev,text_prev,text --fold_length 150 --train_data_path_and_name_and_type exp_owsm/s2t_stats_raw_bpe50000/splits8/text.ctc,text_ctc,text --fold_length 150 --train_data_path_and_name_and_type exp_owsm/s2t_stats_raw_bpe50000/splits8/text,text,text --multiple_iterator true --valid_data_path_and_name_and_type dump/raw/dev_v3/text.prev,text_prev,text --valid_data_path_and_name_and_type dump/raw/dev_v3/text.ctc,text_ctc,text --valid_data_path_and_name_and_type dump/raw/dev_v3/text,text,text --ngpu 8 --multiprocessing_distributed true --dist_launcher slurm --dist_init_method file:///mnt/home/williamchen/espnet/egs2/owsm_v3.1/s2t1/exp_owsm/s2t_train_05b_ds_raw_bpe50000/.dist_init_ee66adec-3a3c-4487-9810-766b99137415 /mnt/home/williamchen/espnet/tools/miniconda/envs/espnet/bin/python3 /mnt/home/williamchen/espnet/espnet2/bin/s2t_train.py --use_preprocessor true --bpemodel data/token_list/bpe_unigram50000/bpe.model --token_type bpe --token_list data/token_list/bpe_unigram50000/tokens.txt --non_linguistic_symbols none --cleaner none --g2p none --valid_data_path_and_name_and_type dump/raw/dev_v3/wav.scp,speech,kaldi_ark --valid_shape_file exp_owsm/s2t_stats_raw_bpe50000/valid/speech_shape --resume true --fold_length 80000 --output_dir exp_owsm/s2t_train_05b_ds_raw_bpe50000 --config conf/train_05b_ds.yaml --frontend_conf fs=16k --normalize=global_mvn --normalize_conf stats_file=exp_owsm/s2t_stats_raw_bpe50000/train/feats_stats.npz --train_data_path_and_name_and_type exp_owsm/s2t_stats_raw_bpe50000/splits8/wav.scp,speech,kaldi_ark --train_shape_file exp_owsm/s2t_stats_raw_bpe50000/splits8/speech_shape --fold_length 150 --train_data_path_and_name_and_type exp_owsm/s2t_stats_raw_bpe50000/splits8/text.prev,text_prev,text --fold_length 150 --train_data_path_and_name_and_type exp_owsm/s2t_stats_raw_bpe50000/splits8/text.ctc,text_ctc,text --fold_length 150 --train_data_path_and_name_and_type exp_owsm/s2t_stats_raw_bpe50000/splits8/text,text,text --multiple_iterator true --valid_data_path_and_name_and_type dump/raw/dev_v3/text.prev,text_prev,text --valid_data_path_and_name_and_type dump/raw/dev_v3/text.ctc,text_ctc,text --valid_data_path_and_name_and_type dump/raw/dev_v3/text,text,text --ngpu 8 --multiprocessing_distributed true --dist_launcher slurm --dist_init_method file:///mnt/home/williamchen/espnet/egs2/owsm_v3.1/s2t1/exp_owsm/s2t_train_05b_ds_raw_bpe50000/.dist_init_ee66adec-3a3c-4487-9810-766b99137415 [2024-12-10 08:39:27,201] [INFO] [real_accelerator.py:219:get_accelerator] Setting ds_accelerator to cuda (auto detect) [2024-12-10 08:39:27,935] [INFO] [real_accelerator.py:219:get_accelerator] Setting ds_accelerator to cuda (auto detect) [2024-12-10 08:39:28,174] [INFO] [real_accelerator.py:219:get_accelerator] Setting ds_accelerator to cuda (auto detect) [2024-12-10 08:39:28,400] [INFO] [real_accelerator.py:219:get_accelerator] Setting ds_accelerator to cuda (auto detect) [2024-12-10 08:39:28,427] [INFO] [real_accelerator.py:219:get_accelerator] Setting ds_accelerator to cuda (auto detect) [2024-12-10 08:39:28,517] [INFO] [real_accelerator.py:219:get_accelerator] Setting ds_accelerator to cuda (auto detect) [2024-12-10 08:39:28,541] [INFO] [real_accelerator.py:219:get_accelerator] Setting ds_accelerator to cuda (auto detect) [2024-12-10 08:39:28,610] [INFO] [real_accelerator.py:219:get_accelerator] Setting ds_accelerator to cuda (auto detect) [2024-12-10 08:39:29,605] [INFO] [real_accelerator.py:219:get_accelerator] Setting ds_accelerator to cuda (auto detect) [2024-12-10 08:39:29,877] [INFO] [real_accelerator.py:219:get_accelerator] Setting ds_accelerator to cuda (auto detect) [2024-12-10 08:39:30,197] [INFO] [real_accelerator.py:219:get_accelerator] Setting ds_accelerator to cuda (auto detect) [2024-12-10 08:39:30,486] [INFO] [real_accelerator.py:219:get_accelerator] Setting ds_accelerator to cuda (auto detect) [2024-12-10 08:39:30,648] [INFO] [real_accelerator.py:219:get_accelerator] Setting ds_accelerator to cuda (auto detect) [2024-12-10 08:39:30,653] [INFO] [real_accelerator.py:219:get_accelerator] Setting ds_accelerator to cuda (auto detect) [2024-12-10 08:39:30,691] [INFO] [real_accelerator.py:219:get_accelerator] Setting ds_accelerator to cuda (auto detect) [2024-12-10 08:39:30,749] [INFO] [real_accelerator.py:219:get_accelerator] Setting ds_accelerator to cuda (auto detect) [W1210 08:39:36.279282004 Utils.hpp:164] Warning: Environment variable NCCL_BLOCKING_WAIT is deprecated; use TORCH_NCCL_BLOCKING_WAIT instead (function operator()) [W1210 08:39:36.851898515 Utils.hpp:164] Warning: Environment variable NCCL_BLOCKING_WAIT is deprecated; use TORCH_NCCL_BLOCKING_WAIT instead (function operator()) [cnode7-008:0/16] 2024-12-10 08:39:36,950 (s2t:462) INFO: Vocabulary size: 50002 [W1210 08:39:37.956096726 Utils.hpp:164] Warning: Environment variable NCCL_BLOCKING_WAIT is deprecated; use TORCH_NCCL_BLOCKING_WAIT instead (function operator()) [W1210 08:39:37.072298061 Utils.hpp:164] Warning: Environment variable NCCL_BLOCKING_WAIT is deprecated; use TORCH_NCCL_BLOCKING_WAIT instead (function operator()) [W1210 08:39:37.466833786 Utils.hpp:164] Warning: Environment variable NCCL_BLOCKING_WAIT is deprecated; use TORCH_NCCL_BLOCKING_WAIT instead (function operator()) [W1210 08:39:37.493781666 Utils.hpp:164] Warning: Environment variable NCCL_BLOCKING_WAIT is deprecated; use TORCH_NCCL_BLOCKING_WAIT instead (function operator()) [W1210 08:39:37.534119571 Utils.hpp:164] Warning: Environment variable NCCL_BLOCKING_WAIT is deprecated; use TORCH_NCCL_BLOCKING_WAIT instead (function operator()) [W1210 08:39:37.549050419 Utils.hpp:164] Warning: Environment variable NCCL_BLOCKING_WAIT is deprecated; use TORCH_NCCL_BLOCKING_WAIT instead (function operator()) [W1210 08:39:38.359904602 Utils.hpp:164] Warning: Environment variable NCCL_BLOCKING_WAIT is deprecated; use TORCH_NCCL_BLOCKING_WAIT instead (function operator()) [W1210 08:39:39.544533179 Utils.hpp:164] Warning: Environment variable NCCL_BLOCKING_WAIT is deprecated; use TORCH_NCCL_BLOCKING_WAIT instead (function operator()) [W1210 08:39:39.668301439 Utils.hpp:164] Warning: Environment variable NCCL_BLOCKING_WAIT is deprecated; use TORCH_NCCL_BLOCKING_WAIT instead (function operator()) [W1210 08:39:39.003476617 Utils.hpp:164] Warning: Environment variable NCCL_BLOCKING_WAIT is deprecated; use TORCH_NCCL_BLOCKING_WAIT instead (function operator()) [W1210 08:39:39.250503772 Utils.hpp:164] Warning: Environment variable NCCL_BLOCKING_WAIT is deprecated; use TORCH_NCCL_BLOCKING_WAIT instead (function operator()) [W1210 08:39:40.512446242 Utils.hpp:164] Warning: Environment variable NCCL_BLOCKING_WAIT is deprecated; use TORCH_NCCL_BLOCKING_WAIT instead (function operator()) [W1210 08:39:40.527704629 Utils.hpp:164] Warning: Environment variable NCCL_BLOCKING_WAIT is deprecated; use TORCH_NCCL_BLOCKING_WAIT instead (function operator()) [W1210 08:39:40.599832669 Utils.hpp:164] Warning: Environment variable NCCL_BLOCKING_WAIT is deprecated; use TORCH_NCCL_BLOCKING_WAIT instead (function operator()) [cnode7-008:0/16] 2024-12-10 08:39:40,583 (abs_task:1383) INFO: pytorch.version=2.4.0+cu121, cuda.available=True, cudnn.version=90100, cudnn.benchmark=False, cudnn.deterministic=True [cnode7-008:0/16] 2024-12-10 08:39:40,588 (abs_task:1384) INFO: Model structure: ESPnetS2TModel( (frontend): DefaultFrontend( (stft): Stft(n_fft=512, win_length=400, hop_length=160, center=True, normalized=False, onesided=True) (frontend): Frontend() (logmel): LogMel(sr=16000, n_fft=512, n_mels=80, fmin=0, fmax=8000.0, htk=False) ) (specaug): SpecAug( (freq_mask): MaskAlongAxis(mask_width_range=[0, 27], num_mask=2, axis=freq) (time_mask): MaskAlongAxisVariableMaxWidth(mask_width_ratio_range=[0.0, 0.05], num_mask=10, axis=time) ) (normalize): GlobalMVN(stats_file=exp_owsm/s2t_stats_raw_bpe50000/train/feats_stats.npz, norm_means=True, norm_vars=True) (encoder): TransformerEncoder( (embed): Conv2dSubsampling( (conv): Sequential( (0): Conv2d(1, 1024, kernel_size=(3, 3), stride=(2, 2)) (1): ReLU() (2): Conv2d(1024, 1024, kernel_size=(3, 3), stride=(2, 2)) (3): ReLU() ) (out): Sequential( (0): Linear(in_features=19456, out_features=1024, bias=True) (1): PositionalEncoding( (dropout): Dropout(p=0.1, inplace=False) ) ) ) (encoders): MultiSequential( (0): EncoderLayer( (self_attn): MultiHeadedAttention( (linear_q): Linear(in_features=1024, out_features=1024, bias=True) (linear_k): Linear(in_features=1024, out_features=1024, bias=True) (linear_v): Linear(in_features=1024, out_features=1024, bias=True) (linear_out): Linear(in_features=1024, out_features=1024, bias=True) (dropout): Identity() (q_norm): Identity() (k_norm): Identity() ) (feed_forward): PositionwiseFeedForward( (w_1): Linear(in_features=1024, out_features=4096, bias=True) (w_2): Linear(in_features=4096, out_features=1024, bias=True) (dropout): Dropout(p=0.1, inplace=False) (activation): ReLU() ) (norm1): LayerNorm((1024,), eps=1e-12, elementwise_affine=True) (norm2): LayerNorm((1024,), eps=1e-12, elementwise_affine=True) (dropout): Dropout(p=0.1, inplace=False) ) (1): EncoderLayer( (self_attn): MultiHeadedAttention( (linear_q): Linear(in_features=1024, out_features=1024, bias=True) (linear_k): Linear(in_features=1024, out_features=1024, bias=True) (linear_v): Linear(in_features=1024, out_features=1024, bias=True) (linear_out): Linear(in_features=1024, out_features=1024, bias=True) (dropout): Identity() (q_norm): Identity() (k_norm): Identity() ) (feed_forward): PositionwiseFeedForward( (w_1): Linear(in_features=1024, out_features=4096, bias=True) (w_2): Linear(in_features=4096, out_features=1024, bias=True) (dropout): Dropout(p=0.1, inplace=False) (activation): ReLU() ) (norm1): LayerNorm((1024,), eps=1e-12, elementwise_affine=True) (norm2): LayerNorm((1024,), eps=1e-12, elementwise_affine=True) (dropout): Dropout(p=0.1, inplace=False) ) (2): EncoderLayer( (self_attn): MultiHeadedAttention( (linear_q): Linear(in_features=1024, out_features=1024, bias=True) (linear_k): Linear(in_features=1024, out_features=1024, bias=True) (linear_v): Linear(in_features=1024, out_features=1024, bias=True) (linear_out): Linear(in_features=1024, out_features=1024, bias=True) (dropout): Identity() (q_norm): Identity() (k_norm): Identity() ) (feed_forward): PositionwiseFeedForward( (w_1): Linear(in_features=1024, out_features=4096, bias=True) (w_2): Linear(in_features=4096, out_features=1024, bias=True) (dropout): Dropout(p=0.1, inplace=False) (activation): ReLU() ) (norm1): LayerNorm((1024,), eps=1e-12, elementwise_affine=True) (norm2): LayerNorm((1024,), eps=1e-12, elementwise_affine=True) (dropout): Dropout(p=0.1, inplace=False) ) (3): EncoderLayer( (self_attn): MultiHeadedAttention( (linear_q): Linear(in_features=1024, out_features=1024, bias=True) (linear_k): Linear(in_features=1024, out_features=1024, bias=True) (linear_v): Linear(in_features=1024, out_features=1024, bias=True) (linear_out): Linear(in_features=1024, out_features=1024, bias=True) (dropout): Identity() (q_norm): Identity() (k_norm): Identity() ) (feed_forward): PositionwiseFeedForward( (w_1): Linear(in_features=1024, out_features=4096, bias=True) (w_2): Linear(in_features=4096, out_features=1024, bias=True) (dropout): Dropout(p=0.1, inplace=False) (activation): ReLU() ) (norm1): LayerNorm((1024,), eps=1e-12, elementwise_affine=True) (norm2): LayerNorm((1024,), eps=1e-12, elementwise_affine=True) (dropout): Dropout(p=0.1, inplace=False) ) (4): EncoderLayer( (self_attn): MultiHeadedAttention( (linear_q): Linear(in_features=1024, out_features=1024, bias=True) (linear_k): Linear(in_features=1024, out_features=1024, bias=True) (linear_v): Linear(in_features=1024, out_features=1024, bias=True) (linear_out): Linear(in_features=1024, out_features=1024, bias=True) (dropout): Identity() (q_norm): Identity() (k_norm): Identity() ) (feed_forward): PositionwiseFeedForward( (w_1): Linear(in_features=1024, out_features=4096, bias=True) (w_2): Linear(in_features=4096, out_features=1024, bias=True) (dropout): Dropout(p=0.1, inplace=False) (activation): ReLU() ) (norm1): LayerNorm((1024,), eps=1e-12, elementwise_affine=True) (norm2): LayerNorm((1024,), eps=1e-12, elementwise_affine=True) (dropout): Dropout(p=0.1, inplace=False) ) (5): EncoderLayer( (self_attn): MultiHeadedAttention( (linear_q): Linear(in_features=1024, out_features=1024, bias=True) (linear_k): Linear(in_features=1024, out_features=1024, bias=True) (linear_v): Linear(in_features=1024, out_features=1024, bias=True) (linear_out): Linear(in_features=1024, out_features=1024, bias=True) (dropout): Identity() (q_norm): Identity() (k_norm): Identity() ) (feed_forward): PositionwiseFeedForward( (w_1): Linear(in_features=1024, out_features=4096, bias=True) (w_2): Linear(in_features=4096, out_features=1024, bias=True) (dropout): Dropout(p=0.1, inplace=False) (activation): ReLU() ) (norm1): LayerNorm((1024,), eps=1e-12, elementwise_affine=True) (norm2): LayerNorm((1024,), eps=1e-12, elementwise_affine=True) (dropout): Dropout(p=0.1, inplace=False) ) (6): EncoderLayer( (self_attn): MultiHeadedAttention( (linear_q): Linear(in_features=1024, out_features=1024, bias=True) (linear_k): Linear(in_features=1024, out_features=1024, bias=True) (linear_v): Linear(in_features=1024, out_features=1024, bias=True) (linear_out): Linear(in_features=1024, out_features=1024, bias=True) (dropout): Identity() (q_norm): Identity() (k_norm): Identity() ) (feed_forward): PositionwiseFeedForward( (w_1): Linear(in_features=1024, out_features=4096, bias=True) (w_2): Linear(in_features=4096, out_features=1024, bias=True) (dropout): Dropout(p=0.1, inplace=False) (activation): ReLU() ) (norm1): LayerNorm((1024,), eps=1e-12, elementwise_affine=True) (norm2): LayerNorm((1024,), eps=1e-12, elementwise_affine=True) (dropout): Dropout(p=0.1, inplace=False) ) (7): EncoderLayer( (self_attn): MultiHeadedAttention( (linear_q): Linear(in_features=1024, out_features=1024, bias=True) (linear_k): Linear(in_features=1024, out_features=1024, bias=True) (linear_v): Linear(in_features=1024, out_features=1024, bias=True) (linear_out): Linear(in_features=1024, out_features=1024, bias=True) (dropout): Identity() (q_norm): Identity() (k_norm): Identity() ) (feed_forward): PositionwiseFeedForward( (w_1): Linear(in_features=1024, out_features=4096, bias=True) (w_2): Linear(in_features=4096, out_features=1024, bias=True) (dropout): Dropout(p=0.1, inplace=False) (activation): ReLU() ) (norm1): LayerNorm((1024,), eps=1e-12, elementwise_affine=True) (norm2): LayerNorm((1024,), eps=1e-12, elementwise_affine=True) (dropout): Dropout(p=0.1, inplace=False) ) (8): EncoderLayer( (self_attn): MultiHeadedAttention( (linear_q): Linear(in_features=1024, out_features=1024, bias=True) (linear_k): Linear(in_features=1024, out_features=1024, bias=True) (linear_v): Linear(in_features=1024, out_features=1024, bias=True) (linear_out): Linear(in_features=1024, out_features=1024, bias=True) (dropout): Identity() (q_norm): Identity() (k_norm): Identity() ) (feed_forward): PositionwiseFeedForward( (w_1): Linear(in_features=1024, out_features=4096, bias=True) (w_2): Linear(in_features=4096, out_features=1024, bias=True) (dropout): Dropout(p=0.1, inplace=False) (activation): ReLU() ) (norm1): LayerNorm((1024,), eps=1e-12, elementwise_affine=True) (norm2): LayerNorm((1024,), eps=1e-12, elementwise_affine=True) (dropout): Dropout(p=0.1, inplace=False) ) (9): EncoderLayer( (self_attn): MultiHeadedAttention( (linear_q): Linear(in_features=1024, out_features=1024, bias=True) (linear_k): Linear(in_features=1024, out_features=1024, bias=True) (linear_v): Linear(in_features=1024, out_features=1024, bias=True) (linear_out): Linear(in_features=1024, out_features=1024, bias=True) (dropout): Identity() (q_norm): Identity() (k_norm): Identity() ) (feed_forward): PositionwiseFeedForward( (w_1): Linear(in_features=1024, out_features=4096, bias=True) (w_2): Linear(in_features=4096, out_features=1024, bias=True) (dropout): Dropout(p=0.1, inplace=False) (activation): ReLU() ) (norm1): LayerNorm((1024,), eps=1e-12, elementwise_affine=True) (norm2): LayerNorm((1024,), eps=1e-12, elementwise_affine=True) (dropout): Dropout(p=0.1, inplace=False) ) (10): EncoderLayer( (self_attn): MultiHeadedAttention( (linear_q): Linear(in_features=1024, out_features=1024, bias=True) (linear_k): Linear(in_features=1024, out_features=1024, bias=True) (linear_v): Linear(in_features=1024, out_features=1024, bias=True) (linear_out): Linear(in_features=1024, out_features=1024, bias=True) (dropout): Identity() (q_norm): Identity() (k_norm): Identity() ) (feed_forward): PositionwiseFeedForward( (w_1): Linear(in_features=1024, out_features=4096, bias=True) (w_2): Linear(in_features=4096, out_features=1024, bias=True) (dropout): Dropout(p=0.1, inplace=False) (activation): ReLU() ) (norm1): LayerNorm((1024,), eps=1e-12, elementwise_affine=True) (norm2): LayerNorm((1024,), eps=1e-12, elementwise_affine=True) (dropout): Dropout(p=0.1, inplace=False) ) (11): EncoderLayer( (self_attn): MultiHeadedAttention( (linear_q): Linear(in_features=1024, out_features=1024, bias=True) (linear_k): Linear(in_features=1024, out_features=1024, bias=True) (linear_v): Linear(in_features=1024, out_features=1024, bias=True) (linear_out): Linear(in_features=1024, out_features=1024, bias=True) (dropout): Identity() (q_norm): Identity() (k_norm): Identity() ) (feed_forward): PositionwiseFeedForward( (w_1): Linear(in_features=1024, out_features=4096, bias=True) (w_2): Linear(in_features=4096, out_features=1024, bias=True) (dropout): Dropout(p=0.1, inplace=False) (activation): ReLU() ) (norm1): LayerNorm((1024,), eps=1e-12, elementwise_affine=True) (norm2): LayerNorm((1024,), eps=1e-12, elementwise_affine=True) (dropout): Dropout(p=0.1, inplace=False) ) (12): EncoderLayer( (self_attn): MultiHeadedAttention( (linear_q): Linear(in_features=1024, out_features=1024, bias=True) (linear_k): Linear(in_features=1024, out_features=1024, bias=True) (linear_v): Linear(in_features=1024, out_features=1024, bias=True) (linear_out): Linear(in_features=1024, out_features=1024, bias=True) (dropout): Identity() (q_norm): Identity() (k_norm): Identity() ) (feed_forward): PositionwiseFeedForward( (w_1): Linear(in_features=1024, out_features=4096, bias=True) (w_2): Linear(in_features=4096, out_features=1024, bias=True) (dropout): Dropout(p=0.1, inplace=False) (activation): ReLU() ) (norm1): LayerNorm((1024,), eps=1e-12, elementwise_affine=True) (norm2): LayerNorm((1024,), eps=1e-12, elementwise_affine=True) (dropout): Dropout(p=0.1, inplace=False) ) (13): EncoderLayer( (self_attn): MultiHeadedAttention( (linear_q): Linear(in_features=1024, out_features=1024, bias=True) (linear_k): Linear(in_features=1024, out_features=1024, bias=True) (linear_v): Linear(in_features=1024, out_features=1024, bias=True) (linear_out): Linear(in_features=1024, out_features=1024, bias=True) (dropout): Identity() (q_norm): Identity() (k_norm): Identity() ) (feed_forward): PositionwiseFeedForward( (w_1): Linear(in_features=1024, out_features=4096, bias=True) (w_2): Linear(in_features=4096, out_features=1024, bias=True) (dropout): Dropout(p=0.1, inplace=False) (activation): ReLU() ) (norm1): LayerNorm((1024,), eps=1e-12, elementwise_affine=True) (norm2): LayerNorm((1024,), eps=1e-12, elementwise_affine=True) (dropout): Dropout(p=0.1, inplace=False) ) (14): EncoderLayer( (self_attn): MultiHeadedAttention( (linear_q): Linear(in_features=1024, out_features=1024, bias=True) (linear_k): Linear(in_features=1024, out_features=1024, bias=True) (linear_v): Linear(in_features=1024, out_features=1024, bias=True) (linear_out): Linear(in_features=1024, out_features=1024, bias=True) (dropout): Identity() (q_norm): Identity() (k_norm): Identity() ) (feed_forward): PositionwiseFeedForward( (w_1): Linear(in_features=1024, out_features=4096, bias=True) (w_2): Linear(in_features=4096, out_features=1024, bias=True) (dropout): Dropout(p=0.1, inplace=False) (activation): ReLU() ) (norm1): LayerNorm((1024,), eps=1e-12, elementwise_affine=True) (norm2): LayerNorm((1024,), eps=1e-12, elementwise_affine=True) (dropout): Dropout(p=0.1, inplace=False) ) (15): EncoderLayer( (self_attn): MultiHeadedAttention( (linear_q): Linear(in_features=1024, out_features=1024, bias=True) (linear_k): Linear(in_features=1024, out_features=1024, bias=True) (linear_v): Linear(in_features=1024, out_features=1024, bias=True) (linear_out): Linear(in_features=1024, out_features=1024, bias=True) (dropout): Identity() (q_norm): Identity() (k_norm): Identity() ) (feed_forward): PositionwiseFeedForward( (w_1): Linear(in_features=1024, out_features=4096, bias=True) (w_2): Linear(in_features=4096, out_features=1024, bias=True) (dropout): Dropout(p=0.1, inplace=False) (activation): ReLU() ) (norm1): LayerNorm((1024,), eps=1e-12, elementwise_affine=True) (norm2): LayerNorm((1024,), eps=1e-12, elementwise_affine=True) (dropout): Dropout(p=0.1, inplace=False) ) ) (after_norm): LayerNorm((1024,), eps=1e-12, elementwise_affine=True) ) (decoder): TransformerDecoder( (embed): Sequential( (0): Embedding(50002, 1024) (1): PositionalEncoding( (dropout): Dropout(p=0.1, inplace=False) ) ) (after_norm): LayerNorm((1024,), eps=1e-12, elementwise_affine=True) (output_layer): Linear(in_features=1024, out_features=50002, bias=True) (decoders): MultiSequential( (0): DecoderLayer( (self_attn): MultiHeadedAttention( (linear_q): Linear(in_features=1024, out_features=1024, bias=True) (linear_k): Linear(in_features=1024, out_features=1024, bias=True) (linear_v): Linear(in_features=1024, out_features=1024, bias=True) (linear_out): Linear(in_features=1024, out_features=1024, bias=True) (dropout): Identity() (q_norm): Identity() (k_norm): Identity() ) (src_attn): MultiHeadedAttention( (linear_q): Linear(in_features=1024, out_features=1024, bias=True) (linear_k): Linear(in_features=1024, out_features=1024, bias=True) (linear_v): Linear(in_features=1024, out_features=1024, bias=True) (linear_out): Linear(in_features=1024, out_features=1024, bias=True) (dropout): Identity() (q_norm): Identity() (k_norm): Identity() ) (feed_forward): PositionwiseFeedForward( (w_1): Linear(in_features=1024, out_features=4096, bias=True) (w_2): Linear(in_features=4096, out_features=1024, bias=True) (dropout): Dropout(p=0.1, inplace=False) (activation): ReLU() ) (norm1): LayerNorm((1024,), eps=1e-12, elementwise_affine=True) (norm2): LayerNorm((1024,), eps=1e-12, elementwise_affine=True) (norm3): LayerNorm((1024,), eps=1e-12, elementwise_affine=True) (dropout): Dropout(p=0.1, inplace=False) ) (1): DecoderLayer( (self_attn): MultiHeadedAttention( (linear_q): Linear(in_features=1024, out_features=1024, bias=True) (linear_k): Linear(in_features=1024, out_features=1024, bias=True) (linear_v): Linear(in_features=1024, out_features=1024, bias=True) (linear_out): Linear(in_features=1024, out_features=1024, bias=True) (dropout): Identity() (q_norm): Identity() (k_norm): Identity() ) (src_attn): MultiHeadedAttention( (linear_q): Linear(in_features=1024, out_features=1024, bias=True) (linear_k): Linear(in_features=1024, out_features=1024, bias=True) (linear_v): Linear(in_features=1024, out_features=1024, bias=True) (linear_out): Linear(in_features=1024, out_features=1024, bias=True) (dropout): Identity() (q_norm): Identity() (k_norm): Identity() ) (feed_forward): PositionwiseFeedForward( (w_1): Linear(in_features=1024, out_features=4096, bias=True) (w_2): Linear(in_features=4096, out_features=1024, bias=True) (dropout): Dropout(p=0.1, inplace=False) (activation): ReLU() ) (norm1): LayerNorm((1024,), eps=1e-12, elementwise_affine=True) (norm2): LayerNorm((1024,), eps=1e-12, elementwise_affine=True) (norm3): LayerNorm((1024,), eps=1e-12, elementwise_affine=True) (dropout): Dropout(p=0.1, inplace=False) ) (2): DecoderLayer( (self_attn): MultiHeadedAttention( (linear_q): Linear(in_features=1024, out_features=1024, bias=True) (linear_k): Linear(in_features=1024, out_features=1024, bias=True) (linear_v): Linear(in_features=1024, out_features=1024, bias=True) (linear_out): Linear(in_features=1024, out_features=1024, bias=True) (dropout): Identity() (q_norm): Identity() (k_norm): Identity() ) (src_attn): MultiHeadedAttention( (linear_q): Linear(in_features=1024, out_features=1024, bias=True) (linear_k): Linear(in_features=1024, out_features=1024, bias=True) (linear_v): Linear(in_features=1024, out_features=1024, bias=True) (linear_out): Linear(in_features=1024, out_features=1024, bias=True) (dropout): Identity() (q_norm): Identity() (k_norm): Identity() ) (feed_forward): PositionwiseFeedForward( (w_1): Linear(in_features=1024, out_features=4096, bias=True) (w_2): Linear(in_features=4096, out_features=1024, bias=True) (dropout): Dropout(p=0.1, inplace=False) (activation): ReLU() ) (norm1): LayerNorm((1024,), eps=1e-12, elementwise_affine=True) (norm2): LayerNorm((1024,), eps=1e-12, elementwise_affine=True) (norm3): LayerNorm((1024,), eps=1e-12, elementwise_affine=True) (dropout): Dropout(p=0.1, inplace=False) ) (3): DecoderLayer( (self_attn): MultiHeadedAttention( (linear_q): Linear(in_features=1024, out_features=1024, bias=True) (linear_k): Linear(in_features=1024, out_features=1024, bias=True) (linear_v): Linear(in_features=1024, out_features=1024, bias=True) (linear_out): Linear(in_features=1024, out_features=1024, bias=True) (dropout): Identity() (q_norm): Identity() (k_norm): Identity() ) (src_attn): MultiHeadedAttention( (linear_q): Linear(in_features=1024, out_features=1024, bias=True) (linear_k): Linear(in_features=1024, out_features=1024, bias=True) (linear_v): Linear(in_features=1024, out_features=1024, bias=True) (linear_out): Linear(in_features=1024, out_features=1024, bias=True) (dropout): Identity() (q_norm): Identity() (k_norm): Identity() ) (feed_forward): PositionwiseFeedForward( (w_1): Linear(in_features=1024, out_features=4096, bias=True) (w_2): Linear(in_features=4096, out_features=1024, bias=True) (dropout): Dropout(p=0.1, inplace=False) (activation): ReLU() ) (norm1): LayerNorm((1024,), eps=1e-12, elementwise_affine=True) (norm2): LayerNorm((1024,), eps=1e-12, elementwise_affine=True) (norm3): LayerNorm((1024,), eps=1e-12, elementwise_affine=True) (dropout): Dropout(p=0.1, inplace=False) ) (4): DecoderLayer( (self_attn): MultiHeadedAttention( (linear_q): Linear(in_features=1024, out_features=1024, bias=True) (linear_k): Linear(in_features=1024, out_features=1024, bias=True) (linear_v): Linear(in_features=1024, out_features=1024, bias=True) (linear_out): Linear(in_features=1024, out_features=1024, bias=True) (dropout): Identity() (q_norm): Identity() (k_norm): Identity() ) (src_attn): MultiHeadedAttention( (linear_q): Linear(in_features=1024, out_features=1024, bias=True) (linear_k): Linear(in_features=1024, out_features=1024, bias=True) (linear_v): Linear(in_features=1024, out_features=1024, bias=True) (linear_out): Linear(in_features=1024, out_features=1024, bias=True) (dropout): Identity() (q_norm): Identity() (k_norm): Identity() ) (feed_forward): PositionwiseFeedForward( (w_1): Linear(in_features=1024, out_features=4096, bias=True) (w_2): Linear(in_features=4096, out_features=1024, bias=True) (dropout): Dropout(p=0.1, inplace=False) (activation): ReLU() ) (norm1): LayerNorm((1024,), eps=1e-12, elementwise_affine=True) (norm2): LayerNorm((1024,), eps=1e-12, elementwise_affine=True) (norm3): LayerNorm((1024,), eps=1e-12, elementwise_affine=True) (dropout): Dropout(p=0.1, inplace=False) ) (5): DecoderLayer( (self_attn): MultiHeadedAttention( (linear_q): Linear(in_features=1024, out_features=1024, bias=True) (linear_k): Linear(in_features=1024, out_features=1024, bias=True) (linear_v): Linear(in_features=1024, out_features=1024, bias=True) (linear_out): Linear(in_features=1024, out_features=1024, bias=True) (dropout): Identity() (q_norm): Identity() (k_norm): Identity() ) (src_attn): MultiHeadedAttention( (linear_q): Linear(in_features=1024, out_features=1024, bias=True) (linear_k): Linear(in_features=1024, out_features=1024, bias=True) (linear_v): Linear(in_features=1024, out_features=1024, bias=True) (linear_out): Linear(in_features=1024, out_features=1024, bias=True) (dropout): Identity() (q_norm): Identity() (k_norm): Identity() ) (feed_forward): PositionwiseFeedForward( (w_1): Linear(in_features=1024, out_features=4096, bias=True) (w_2): Linear(in_features=4096, out_features=1024, bias=True) (dropout): Dropout(p=0.1, inplace=False) (activation): ReLU() ) (norm1): LayerNorm((1024,), eps=1e-12, elementwise_affine=True) (norm2): LayerNorm((1024,), eps=1e-12, elementwise_affine=True) (norm3): LayerNorm((1024,), eps=1e-12, elementwise_affine=True) (dropout): Dropout(p=0.1, inplace=False) ) (6): DecoderLayer( (self_attn): MultiHeadedAttention( (linear_q): Linear(in_features=1024, out_features=1024, bias=True) (linear_k): Linear(in_features=1024, out_features=1024, bias=True) (linear_v): Linear(in_features=1024, out_features=1024, bias=True) (linear_out): Linear(in_features=1024, out_features=1024, bias=True) (dropout): Identity() (q_norm): Identity() (k_norm): Identity() ) (src_attn): MultiHeadedAttention( (linear_q): Linear(in_features=1024, out_features=1024, bias=True) (linear_k): Linear(in_features=1024, out_features=1024, bias=True) (linear_v): Linear(in_features=1024, out_features=1024, bias=True) (linear_out): Linear(in_features=1024, out_features=1024, bias=True) (dropout): Identity() (q_norm): Identity() (k_norm): Identity() ) (feed_forward): PositionwiseFeedForward( (w_1): Linear(in_features=1024, out_features=4096, bias=True) (w_2): Linear(in_features=4096, out_features=1024, bias=True) (dropout): Dropout(p=0.1, inplace=False) (activation): ReLU() ) (norm1): LayerNorm((1024,), eps=1e-12, elementwise_affine=True) (norm2): LayerNorm((1024,), eps=1e-12, elementwise_affine=True) (norm3): LayerNorm((1024,), eps=1e-12, elementwise_affine=True) (dropout): Dropout(p=0.1, inplace=False) ) (7): DecoderLayer( (self_attn): MultiHeadedAttention( (linear_q): Linear(in_features=1024, out_features=1024, bias=True) (linear_k): Linear(in_features=1024, out_features=1024, bias=True) (linear_v): Linear(in_features=1024, out_features=1024, bias=True) (linear_out): Linear(in_features=1024, out_features=1024, bias=True) (dropout): Identity() (q_norm): Identity() (k_norm): Identity() ) (src_attn): MultiHeadedAttention( (linear_q): Linear(in_features=1024, out_features=1024, bias=True) (linear_k): Linear(in_features=1024, out_features=1024, bias=True) (linear_v): Linear(in_features=1024, out_features=1024, bias=True) (linear_out): Linear(in_features=1024, out_features=1024, bias=True) (dropout): Identity() (q_norm): Identity() (k_norm): Identity() ) (feed_forward): PositionwiseFeedForward( (w_1): Linear(in_features=1024, out_features=4096, bias=True) (w_2): Linear(in_features=4096, out_features=1024, bias=True) (dropout): Dropout(p=0.1, inplace=False) (activation): ReLU() ) (norm1): LayerNorm((1024,), eps=1e-12, elementwise_affine=True) (norm2): LayerNorm((1024,), eps=1e-12, elementwise_affine=True) (norm3): LayerNorm((1024,), eps=1e-12, elementwise_affine=True) (dropout): Dropout(p=0.1, inplace=False) ) (8): DecoderLayer( (self_attn): MultiHeadedAttention( (linear_q): Linear(in_features=1024, out_features=1024, bias=True) (linear_k): Linear(in_features=1024, out_features=1024, bias=True) (linear_v): Linear(in_features=1024, out_features=1024, bias=True) (linear_out): Linear(in_features=1024, out_features=1024, bias=True) (dropout): Identity() (q_norm): Identity() (k_norm): Identity() ) (src_attn): MultiHeadedAttention( (linear_q): Linear(in_features=1024, out_features=1024, bias=True) (linear_k): Linear(in_features=1024, out_features=1024, bias=True) (linear_v): Linear(in_features=1024, out_features=1024, bias=True) (linear_out): Linear(in_features=1024, out_features=1024, bias=True) (dropout): Identity() (q_norm): Identity() (k_norm): Identity() ) (feed_forward): PositionwiseFeedForward( (w_1): Linear(in_features=1024, out_features=4096, bias=True) (w_2): Linear(in_features=4096, out_features=1024, bias=True) (dropout): Dropout(p=0.1, inplace=False) (activation): ReLU() ) (norm1): LayerNorm((1024,), eps=1e-12, elementwise_affine=True) (norm2): LayerNorm((1024,), eps=1e-12, elementwise_affine=True) (norm3): LayerNorm((1024,), eps=1e-12, elementwise_affine=True) (dropout): Dropout(p=0.1, inplace=False) ) (9): DecoderLayer( (self_attn): MultiHeadedAttention( (linear_q): Linear(in_features=1024, out_features=1024, bias=True) (linear_k): Linear(in_features=1024, out_features=1024, bias=True) (linear_v): Linear(in_features=1024, out_features=1024, bias=True) (linear_out): Linear(in_features=1024, out_features=1024, bias=True) (dropout): Identity() (q_norm): Identity() (k_norm): Identity() ) (src_attn): MultiHeadedAttention( (linear_q): Linear(in_features=1024, out_features=1024, bias=True) (linear_k): Linear(in_features=1024, out_features=1024, bias=True) (linear_v): Linear(in_features=1024, out_features=1024, bias=True) (linear_out): Linear(in_features=1024, out_features=1024, bias=True) (dropout): Identity() (q_norm): Identity() (k_norm): Identity() ) (feed_forward): PositionwiseFeedForward( (w_1): Linear(in_features=1024, out_features=4096, bias=True) (w_2): Linear(in_features=4096, out_features=1024, bias=True) (dropout): Dropout(p=0.1, inplace=False) (activation): ReLU() ) (norm1): LayerNorm((1024,), eps=1e-12, elementwise_affine=True) (norm2): LayerNorm((1024,), eps=1e-12, elementwise_affine=True) (norm3): LayerNorm((1024,), eps=1e-12, elementwise_affine=True) (dropout): Dropout(p=0.1, inplace=False) ) (10): DecoderLayer( (self_attn): MultiHeadedAttention( (linear_q): Linear(in_features=1024, out_features=1024, bias=True) (linear_k): Linear(in_features=1024, out_features=1024, bias=True) (linear_v): Linear(in_features=1024, out_features=1024, bias=True) (linear_out): Linear(in_features=1024, out_features=1024, bias=True) (dropout): Identity() (q_norm): Identity() (k_norm): Identity() ) (src_attn): MultiHeadedAttention( (linear_q): Linear(in_features=1024, out_features=1024, bias=True) (linear_k): Linear(in_features=1024, out_features=1024, bias=True) (linear_v): Linear(in_features=1024, out_features=1024, bias=True) (linear_out): Linear(in_features=1024, out_features=1024, bias=True) (dropout): Identity() (q_norm): Identity() (k_norm): Identity() ) (feed_forward): PositionwiseFeedForward( (w_1): Linear(in_features=1024, out_features=4096, bias=True) (w_2): Linear(in_features=4096, out_features=1024, bias=True) (dropout): Dropout(p=0.1, inplace=False) (activation): ReLU() ) (norm1): LayerNorm((1024,), eps=1e-12, elementwise_affine=True) (norm2): LayerNorm((1024,), eps=1e-12, elementwise_affine=True) (norm3): LayerNorm((1024,), eps=1e-12, elementwise_affine=True) (dropout): Dropout(p=0.1, inplace=False) ) (11): DecoderLayer( (self_attn): MultiHeadedAttention( (linear_q): Linear(in_features=1024, out_features=1024, bias=True) (linear_k): Linear(in_features=1024, out_features=1024, bias=True) (linear_v): Linear(in_features=1024, out_features=1024, bias=True) (linear_out): Linear(in_features=1024, out_features=1024, bias=True) (dropout): Identity() (q_norm): Identity() (k_norm): Identity() ) (src_attn): MultiHeadedAttention( (linear_q): Linear(in_features=1024, out_features=1024, bias=True) (linear_k): Linear(in_features=1024, out_features=1024, bias=True) (linear_v): Linear(in_features=1024, out_features=1024, bias=True) (linear_out): Linear(in_features=1024, out_features=1024, bias=True) (dropout): Identity() (q_norm): Identity() (k_norm): Identity() ) (feed_forward): PositionwiseFeedForward( (w_1): Linear(in_features=1024, out_features=4096, bias=True) (w_2): Linear(in_features=4096, out_features=1024, bias=True) (dropout): Dropout(p=0.1, inplace=False) (activation): ReLU() ) (norm1): LayerNorm((1024,), eps=1e-12, elementwise_affine=True) (norm2): LayerNorm((1024,), eps=1e-12, elementwise_affine=True) (norm3): LayerNorm((1024,), eps=1e-12, elementwise_affine=True) (dropout): Dropout(p=0.1, inplace=False) ) (12): DecoderLayer( (self_attn): MultiHeadedAttention( (linear_q): Linear(in_features=1024, out_features=1024, bias=True) (linear_k): Linear(in_features=1024, out_features=1024, bias=True) (linear_v): Linear(in_features=1024, out_features=1024, bias=True) (linear_out): Linear(in_features=1024, out_features=1024, bias=True) (dropout): Identity() (q_norm): Identity() (k_norm): Identity() ) (src_attn): MultiHeadedAttention( (linear_q): Linear(in_features=1024, out_features=1024, bias=True) (linear_k): Linear(in_features=1024, out_features=1024, bias=True) (linear_v): Linear(in_features=1024, out_features=1024, bias=True) (linear_out): Linear(in_features=1024, out_features=1024, bias=True) (dropout): Identity() (q_norm): Identity() (k_norm): Identity() ) (feed_forward): PositionwiseFeedForward( (w_1): Linear(in_features=1024, out_features=4096, bias=True) (w_2): Linear(in_features=4096, out_features=1024, bias=True) (dropout): Dropout(p=0.1, inplace=False) (activation): ReLU() ) (norm1): LayerNorm((1024,), eps=1e-12, elementwise_affine=True) (norm2): LayerNorm((1024,), eps=1e-12, elementwise_affine=True) (norm3): LayerNorm((1024,), eps=1e-12, elementwise_affine=True) (dropout): Dropout(p=0.1, inplace=False) ) (13): DecoderLayer( (self_attn): MultiHeadedAttention( (linear_q): Linear(in_features=1024, out_features=1024, bias=True) (linear_k): Linear(in_features=1024, out_features=1024, bias=True) (linear_v): Linear(in_features=1024, out_features=1024, bias=True) (linear_out): Linear(in_features=1024, out_features=1024, bias=True) (dropout): Identity() (q_norm): Identity() (k_norm): Identity() ) (src_attn): MultiHeadedAttention( (linear_q): Linear(in_features=1024, out_features=1024, bias=True) (linear_k): Linear(in_features=1024, out_features=1024, bias=True) (linear_v): Linear(in_features=1024, out_features=1024, bias=True) (linear_out): Linear(in_features=1024, out_features=1024, bias=True) (dropout): Identity() (q_norm): Identity() (k_norm): Identity() ) (feed_forward): PositionwiseFeedForward( (w_1): Linear(in_features=1024, out_features=4096, bias=True) (w_2): Linear(in_features=4096, out_features=1024, bias=True) (dropout): Dropout(p=0.1, inplace=False) (activation): ReLU() ) (norm1): LayerNorm((1024,), eps=1e-12, elementwise_affine=True) (norm2): LayerNorm((1024,), eps=1e-12, elementwise_affine=True) (norm3): LayerNorm((1024,), eps=1e-12, elementwise_affine=True) (dropout): Dropout(p=0.1, inplace=False) ) (14): DecoderLayer( (self_attn): MultiHeadedAttention( (linear_q): Linear(in_features=1024, out_features=1024, bias=True) (linear_k): Linear(in_features=1024, out_features=1024, bias=True) (linear_v): Linear(in_features=1024, out_features=1024, bias=True) (linear_out): Linear(in_features=1024, out_features=1024, bias=True) (dropout): Identity() (q_norm): Identity() (k_norm): Identity() ) (src_attn): MultiHeadedAttention( (linear_q): Linear(in_features=1024, out_features=1024, bias=True) (linear_k): Linear(in_features=1024, out_features=1024, bias=True) (linear_v): Linear(in_features=1024, out_features=1024, bias=True) (linear_out): Linear(in_features=1024, out_features=1024, bias=True) (dropout): Identity() (q_norm): Identity() (k_norm): Identity() ) (feed_forward): PositionwiseFeedForward( (w_1): Linear(in_features=1024, out_features=4096, bias=True) (w_2): Linear(in_features=4096, out_features=1024, bias=True) (dropout): Dropout(p=0.1, inplace=False) (activation): ReLU() ) (norm1): LayerNorm((1024,), eps=1e-12, elementwise_affine=True) (norm2): LayerNorm((1024,), eps=1e-12, elementwise_affine=True) (norm3): LayerNorm((1024,), eps=1e-12, elementwise_affine=True) (dropout): Dropout(p=0.1, inplace=False) ) (15): DecoderLayer( (self_attn): MultiHeadedAttention( (linear_q): Linear(in_features=1024, out_features=1024, bias=True) (linear_k): Linear(in_features=1024, out_features=1024, bias=True) (linear_v): Linear(in_features=1024, out_features=1024, bias=True) (linear_out): Linear(in_features=1024, out_features=1024, bias=True) (dropout): Identity() (q_norm): Identity() (k_norm): Identity() ) (src_attn): MultiHeadedAttention( (linear_q): Linear(in_features=1024, out_features=1024, bias=True) (linear_k): Linear(in_features=1024, out_features=1024, bias=True) (linear_v): Linear(in_features=1024, out_features=1024, bias=True) (linear_out): Linear(in_features=1024, out_features=1024, bias=True) (dropout): Identity() (q_norm): Identity() (k_norm): Identity() ) (feed_forward): PositionwiseFeedForward( (w_1): Linear(in_features=1024, out_features=4096, bias=True) (w_2): Linear(in_features=4096, out_features=1024, bias=True) (dropout): Dropout(p=0.1, inplace=False) (activation): ReLU() ) (norm1): LayerNorm((1024,), eps=1e-12, elementwise_affine=True) (norm2): LayerNorm((1024,), eps=1e-12, elementwise_affine=True) (norm3): LayerNorm((1024,), eps=1e-12, elementwise_affine=True) (dropout): Dropout(p=0.1, inplace=False) ) ) ) (criterion_att): LabelSmoothingLoss( (criterion): KLDivLoss() ) (ctc): CTC( (ctc_lo): Linear(in_features=1024, out_features=50002, bias=True) (ctc_loss): CTCLoss() ) ) Model summary: Class Name: ESPnetS2TModel Total Number of model parameters: 653.37 M Number of trainable parameters: 653.37 M (100.0%) Size: 2.61 GB Type: torch.float32 [cnode7-008:0/16] 2024-12-10 08:39:40,589 (abs_task:1387) INFO: Optimizer: Adadelta ( Parameter Group 0 capturable: False differentiable: False eps: 1e-06 foreach: None lr: 1.0 maximize: False rho: 0.9 weight_decay: 0 ) [cnode7-008:0/16] 2024-12-10 08:39:40,589 (abs_task:1388) INFO: Scheduler: None [cnode7-008:0/16] 2024-12-10 08:39:40,593 (abs_task:1397) INFO: Saving the configuration in exp_owsm/s2t_train_05b_ds_raw_bpe50000/config.yaml [cnode7-008:0/16] 2024-12-10 08:39:45,287 (s2t:444) INFO: Optional Data Names: ('text_prev', 'text_ctc', 'text_spk2', 'text_spk3', 'text_spk4') /mnt/home/williamchen/espnet/espnet2/train/deepspeed_trainer.py:240: InstrumentationWarning: @typechecked only supports instrumenting functions wrapped with @classmethod, @staticmethod or @property -- not typechecking espnet2.train.deepspeed_trainer.DeepSpeedTrainer.valid_one_epoch def valid_one_epoch( [2024-12-10 08:39:47,742] [INFO] [comm.py:652:init_distributed] cdb=None [2024-12-10 08:39:47,749] [INFO] [config.py:733:__init__] Config mesh_device None world_size = 16 /mnt/home/williamchen/espnet/espnet2/train/deepspeed_trainer.py:240: InstrumentationWarning: @typechecked only supports instrumenting functions wrapped with @classmethod, @staticmethod or @property -- not typechecking espnet2.train.deepspeed_trainer.DeepSpeedTrainer.valid_one_epoch def valid_one_epoch( [2024-12-10 08:39:48,011] [INFO] [comm.py:652:init_distributed] cdb=None [2024-12-10 08:39:48,013] [INFO] [config.py:733:__init__] Config mesh_device None world_size = 16 /mnt/home/williamchen/espnet/espnet2/train/deepspeed_trainer.py:240: InstrumentationWarning: @typechecked only supports instrumenting functions wrapped with @classmethod, @staticmethod or @property -- not typechecking espnet2.train.deepspeed_trainer.DeepSpeedTrainer.valid_one_epoch def valid_one_epoch( [cnode7-008:0/16] 2024-12-10 08:39:48,661 (abs_task:1807) INFO: [valid] dataset: ESPnetDataset( speech: {"path": "dump/raw/dev_v3/wav.scp", "type": "kaldi_ark"} text_prev: {"path": "dump/raw/dev_v3/text.prev", "type": "text"} text_ctc: {"path": "dump/raw/dev_v3/text.ctc", "type": "text"} text: {"path": "dump/raw/dev_v3/text", "type": "text"} preprocess: ) [cnode7-008:0/16] 2024-12-10 08:39:48,661 (abs_task:1808) INFO: [valid] Batch sampler: SortedBatchSampler(N-batch=74743, batch_size=16, shape_file=exp_owsm/s2t_stats_raw_bpe50000/valid/speech_shape, sort_in_batch=descending, sort_batch=descending) [cnode7-008:0/16] 2024-12-10 08:39:48,667 (abs_task:1809) INFO: [valid] mini-batch sizes summary: N-batch=74743, mean=16.0, min=16, max=17 /mnt/home/williamchen/espnet/espnet2/train/deepspeed_trainer.py:240: InstrumentationWarning: @typechecked only supports instrumenting functions wrapped with @classmethod, @staticmethod or @property -- not typechecking espnet2.train.deepspeed_trainer.DeepSpeedTrainer.valid_one_epoch def valid_one_epoch( /mnt/home/williamchen/espnet/espnet2/train/deepspeed_trainer.py:240: InstrumentationWarning: @typechecked only supports instrumenting functions wrapped with @classmethod, @staticmethod or @property -- not typechecking espnet2.train.deepspeed_trainer.DeepSpeedTrainer.valid_one_epoch def valid_one_epoch( [cnode7-008:0/16] 2024-12-10 08:39:48,724 (distributed_utils:129) WARNING: ================================================================= Found OMP_NUM_THREADS=1 in environment variables. With some advanced features, DeepSpeed may have heavy cpu workload so that OMP_NUM_THREADS=1 is not sufficient. Try to increase it in your path.sh ================================================================= [2024-12-10 08:39:48,724] [INFO] [comm.py:652:init_distributed] cdb=None [2024-12-10 08:39:48,725] [INFO] [logging.py:129:log_dist] [Rank 0] DeepSpeed info: version=0.15.3, git-hash=unknown, git-branch=unknown [2024-12-10 08:39:48,725] [INFO] [config.py:733:__init__] Config mesh_device None world_size = 16 [2024-12-10 08:39:48,775] [INFO] [comm.py:652:init_distributed] cdb=None [2024-12-10 08:39:48,776] [INFO] [config.py:733:__init__] Config mesh_device None world_size = 16 cnode7-008:628123:628123 [0] NCCL INFO NCCL_SOCKET_IFNAME set by environment to ^lo,docker,virbr,vmnet,vboxnet cnode7-008:628123:628123 [0] NCCL INFO Bootstrap : Using enp170s0np0:10.225.1.170<0> cnode7-008:628123:628123 [0] NCCL INFO NET/Plugin : dlerror=libnccl-net.so: cannot open shared object file: No such file or directory No plugin found (libnccl-net.so), using internal implementation cnode7-008:628123:628123 [0] NCCL INFO cudaDriverVersion 12020 NCCL version 2.20.5+cuda12.4 /mnt/home/williamchen/espnet/espnet2/train/deepspeed_trainer.py:240: InstrumentationWarning: @typechecked only supports instrumenting functions wrapped with @classmethod, @staticmethod or @property -- not typechecking espnet2.train.deepspeed_trainer.DeepSpeedTrainer.valid_one_epoch def valid_one_epoch( /mnt/home/williamchen/espnet/espnet2/train/deepspeed_trainer.py:240: InstrumentationWarning: @typechecked only supports instrumenting functions wrapped with @classmethod, @staticmethod or @property -- not typechecking espnet2.train.deepspeed_trainer.DeepSpeedTrainer.valid_one_epoch def valid_one_epoch( [2024-12-10 08:39:48,828] [INFO] [comm.py:652:init_distributed] cdb=None [2024-12-10 08:39:48,829] [INFO] [config.py:733:__init__] Config mesh_device None world_size = 16 /mnt/home/williamchen/espnet/espnet2/train/deepspeed_trainer.py:240: InstrumentationWarning: @typechecked only supports instrumenting functions wrapped with @classmethod, @staticmethod or @property -- not typechecking espnet2.train.deepspeed_trainer.DeepSpeedTrainer.valid_one_epoch def valid_one_epoch( cnode7-008:628124:628124 [1] NCCL INFO cudaDriverVersion 12020 cnode7-008:628124:628124 [1] NCCL INFO NCCL_SOCKET_IFNAME set by environment to ^lo,docker,virbr,vmnet,vboxnet cnode7-008:628124:628124 [1] NCCL INFO Bootstrap : Using enp170s0np0:10.225.1.170<0> cnode7-008:628124:628124 [1] NCCL INFO NET/Plugin : dlerror=libnccl-net.so: cannot open shared object file: No such file or directory No plugin found (libnccl-net.so), using internal implementation cnode7-008:628130:628130 [7] NCCL INFO cudaDriverVersion 12020 cnode7-008:628130:628130 [7] NCCL INFO NCCL_SOCKET_IFNAME set by environment to ^lo,docker,virbr,vmnet,vboxnet cnode7-008:628130:628130 [7] NCCL INFO Bootstrap : Using enp170s0np0:10.225.1.170<0> cnode7-008:628130:628130 [7] NCCL INFO NET/Plugin : dlerror=libnccl-net.so: cannot open shared object file: No such file or directory No plugin found (libnccl-net.so), using internal implementation cnode7-008:628128:628128 [5] NCCL INFO cudaDriverVersion 12020 cnode7-008:628128:628128 [5] NCCL INFO NCCL_SOCKET_IFNAME set by environment to ^lo,docker,virbr,vmnet,vboxnet cnode7-008:628128:628128 [5] NCCL INFO Bootstrap : Using enp170s0np0:10.225.1.170<0> cnode7-008:628128:628128 [5] NCCL INFO NET/Plugin : dlerror=libnccl-net.so: cannot open shared object file: No such file or directory No plugin found (libnccl-net.so), using internal implementation [2024-12-10 08:39:48,895] [INFO] [comm.py:652:init_distributed] cdb=None [2024-12-10 08:39:48,898] [INFO] [config.py:733:__init__] Config mesh_device None world_size = 16 cnode7-008:628126:628126 [3] NCCL INFO cudaDriverVersion 12020 cnode7-008:628126:628126 [3] NCCL INFO NCCL_SOCKET_IFNAME set by environment to ^lo,docker,virbr,vmnet,vboxnet cnode7-008:628126:628126 [3] NCCL INFO Bootstrap : Using enp170s0np0:10.225.1.170<0> cnode7-008:628126:628126 [3] NCCL INFO NET/Plugin : dlerror=libnccl-net.so: cannot open shared object file: No such file or directory No plugin found (libnccl-net.so), using internal implementation [2024-12-10 08:39:48,995] [INFO] [comm.py:652:init_distributed] cdb=None [2024-12-10 08:39:48,997] [INFO] [config.py:733:__init__] Config mesh_device None world_size = 16 [2024-12-10 08:39:49,003] [INFO] [comm.py:652:init_distributed] cdb=None [2024-12-10 08:39:49,004] [INFO] [config.py:733:__init__] Config mesh_device None world_size = 16 cnode7-008:628129:628129 [6] NCCL INFO cudaDriverVersion 12020 cnode7-008:628129:628129 [6] NCCL INFO NCCL_SOCKET_IFNAME set by environment to ^lo,docker,virbr,vmnet,vboxnet cnode7-008:628129:628129 [6] NCCL INFO Bootstrap : Using enp170s0np0:10.225.1.170<0> cnode7-008:628129:628129 [6] NCCL INFO NET/Plugin : dlerror=libnccl-net.so: cannot open shared object file: No such file or directory No plugin found (libnccl-net.so), using internal implementation cnode7-008:628127:628127 [4] NCCL INFO cudaDriverVersion 12020 cnode7-008:628127:628127 [4] NCCL INFO NCCL_SOCKET_IFNAME set by environment to ^lo,docker,virbr,vmnet,vboxnet cnode7-008:628127:628127 [4] NCCL INFO Bootstrap : Using enp170s0np0:10.225.1.170<0> cnode7-008:628127:628127 [4] NCCL INFO NET/Plugin : dlerror=libnccl-net.so: cannot open shared object file: No such file or directory No plugin found (libnccl-net.so), using internal implementation cnode7-008:628125:628125 [2] NCCL INFO cudaDriverVersion 12020 cnode7-008:628125:628125 [2] NCCL INFO NCCL_SOCKET_IFNAME set by environment to ^lo,docker,virbr,vmnet,vboxnet cnode7-008:628125:628125 [2] NCCL INFO Bootstrap : Using enp170s0np0:10.225.1.170<0> cnode7-008:628125:628125 [2] NCCL INFO NET/Plugin : dlerror=libnccl-net.so: cannot open shared object file: No such file or directory No plugin found (libnccl-net.so), using internal implementation cnode7-008:628124:628983 [1] NCCL INFO NCCL_SOCKET_IFNAME set by environment to ^lo,docker,virbr,vmnet,vboxnet cnode7-008:628123:628980 [0] NCCL INFO NCCL_SOCKET_IFNAME set by environment to ^lo,docker,virbr,vmnet,vboxnet cnode7-008:628130:628985 [7] NCCL INFO NCCL_SOCKET_IFNAME set by environment to ^lo,docker,virbr,vmnet,vboxnet cnode7-008:628128:628988 [5] NCCL INFO NCCL_SOCKET_IFNAME set by environment to ^lo,docker,virbr,vmnet,vboxnet cnode7-008:628126:628984 [3] NCCL INFO NCCL_SOCKET_IFNAME set by environment to ^lo,docker,virbr,vmnet,vboxnet cnode7-008:628129:628991 [6] NCCL INFO NCCL_SOCKET_IFNAME set by environment to ^lo,docker,virbr,vmnet,vboxnet cnode7-008:628129:628991 [6] NCCL INFO NET/IB : Using [0]mlx5_0:1/IB [1]mlx5_3:1/IB [2]mlx5_4:1/IB [3]mlx5_5:1/IB [4]mlx5_6:1/IB [5]mlx5_7:1/RoCE [6]mlx5_8:1/IB [7]mlx5_9:1/IB [8]mlx5_10:1/IB [RO]; OOB enp170s0np0:10.225.1.170<0> cnode7-008:628129:628991 [6] NCCL INFO Using non-device net plugin version 0 cnode7-008:628129:628991 [6] NCCL INFO Using network IB cnode7-008:628124:628983 [1] NCCL INFO NET/IB : Using [0]mlx5_0:1/IB [1]mlx5_3:1/IB [2]mlx5_4:1/IB [3]mlx5_5:1/IB [4]mlx5_6:1/IB [5]mlx5_7:1/RoCE [6]mlx5_8:1/IB [7]mlx5_9:1/IB [8]mlx5_10:1/IB [RO]; OOB enp170s0np0:10.225.1.170<0> cnode7-008:628124:628983 [1] NCCL INFO Using non-device net plugin version 0 cnode7-008:628124:628983 [1] NCCL INFO Using network IB cnode7-008:628123:628980 [0] NCCL INFO NET/IB : Using [0]mlx5_0:1/IB [1]mlx5_3:1/IB [2]mlx5_4:1/IB [3]mlx5_5:1/IB [4]mlx5_6:1/IB [5]mlx5_7:1/RoCE [6]mlx5_8:1/IB [7]mlx5_9:1/IB [8]mlx5_10:1/IB [RO]; OOB enp170s0np0:10.225.1.170<0> cnode7-008:628123:628980 [0] NCCL INFO Using non-device net plugin version 0 cnode7-008:628123:628980 [0] NCCL INFO Using network IB cnode7-008:628130:628985 [7] NCCL INFO NET/IB : Using [0]mlx5_0:1/IB [1]mlx5_3:1/IB [2]mlx5_4:1/IB [3]mlx5_5:1/IB [4]mlx5_6:1/IB [5]mlx5_7:1/RoCE [6]mlx5_8:1/IB [7]mlx5_9:1/IB [8]mlx5_10:1/IB [RO]; OOB enp170s0np0:10.225.1.170<0> cnode7-008:628130:628985 [7] NCCL INFO Using non-device net plugin version 0 cnode7-008:628130:628985 [7] NCCL INFO Using network IB cnode7-008:628128:628988 [5] NCCL INFO NET/IB : Using [0]mlx5_0:1/IB [1]mlx5_3:1/IB [2]mlx5_4:1/IB [3]mlx5_5:1/IB [4]mlx5_6:1/IB [5]mlx5_7:1/RoCE [6]mlx5_8:1/IB [7]mlx5_9:1/IB [8]mlx5_10:1/IB [RO]; OOB enp170s0np0:10.225.1.170<0> cnode7-008:628128:628988 [5] NCCL INFO Using non-device net plugin version 0 cnode7-008:628128:628988 [5] NCCL INFO Using network IB cnode7-008:628126:628984 [3] NCCL INFO NET/IB : Using [0]mlx5_0:1/IB [1]mlx5_3:1/IB [2]mlx5_4:1/IB [3]mlx5_5:1/IB [4]mlx5_6:1/IB [5]mlx5_7:1/RoCE [6]mlx5_8:1/IB [7]mlx5_9:1/IB [8]mlx5_10:1/IB [RO]; OOB enp170s0np0:10.225.1.170<0> cnode7-008:628126:628984 [3] NCCL INFO Using non-device net plugin version 0 cnode7-008:628126:628984 [3] NCCL INFO Using network IB cnode7-008:628127:628996 [4] NCCL INFO NCCL_SOCKET_IFNAME set by environment to ^lo,docker,virbr,vmnet,vboxnet cnode7-008:628127:628996 [4] NCCL INFO NET/IB : Using [0]mlx5_0:1/IB [1]mlx5_3:1/IB [2]mlx5_4:1/IB [3]mlx5_5:1/IB [4]mlx5_6:1/IB [5]mlx5_7:1/RoCE [6]mlx5_8:1/IB [7]mlx5_9:1/IB [8]mlx5_10:1/IB [RO]; OOB enp170s0np0:10.225.1.170<0> cnode7-008:628127:628996 [4] NCCL INFO Using non-device net plugin version 0 cnode7-008:628127:628996 [4] NCCL INFO Using network IB cnode7-008:628125:628997 [2] NCCL INFO NCCL_SOCKET_IFNAME set by environment to ^lo,docker,virbr,vmnet,vboxnet cnode7-008:628125:628997 [2] NCCL INFO NET/IB : Using [0]mlx5_0:1/IB [1]mlx5_3:1/IB [2]mlx5_4:1/IB [3]mlx5_5:1/IB [4]mlx5_6:1/IB [5]mlx5_7:1/RoCE [6]mlx5_8:1/IB [7]mlx5_9:1/IB [8]mlx5_10:1/IB [RO]; OOB enp170s0np0:10.225.1.170<0> cnode7-008:628125:628997 [2] NCCL INFO Using non-device net plugin version 0 cnode7-008:628125:628997 [2] NCCL INFO Using network IB /mnt/home/williamchen/espnet/espnet2/train/deepspeed_trainer.py:240: InstrumentationWarning: @typechecked only supports instrumenting functions wrapped with @classmethod, @staticmethod or @property -- not typechecking espnet2.train.deepspeed_trainer.DeepSpeedTrainer.valid_one_epoch def valid_one_epoch( /mnt/home/williamchen/espnet/espnet2/train/deepspeed_trainer.py:240: InstrumentationWarning: @typechecked only supports instrumenting functions wrapped with @classmethod, @staticmethod or @property -- not typechecking espnet2.train.deepspeed_trainer.DeepSpeedTrainer.valid_one_epoch def valid_one_epoch( [2024-12-10 08:39:50,842] [INFO] [comm.py:652:init_distributed] cdb=None [2024-12-10 08:39:50,845] [INFO] [config.py:733:__init__] Config mesh_device None world_size = 16 /mnt/home/williamchen/espnet/espnet2/train/deepspeed_trainer.py:240: InstrumentationWarning: @typechecked only supports instrumenting functions wrapped with @classmethod, @staticmethod or @property -- not typechecking espnet2.train.deepspeed_trainer.DeepSpeedTrainer.valid_one_epoch def valid_one_epoch( [2024-12-10 08:39:50,870] [INFO] [comm.py:652:init_distributed] cdb=None [2024-12-10 08:39:50,872] [INFO] [config.py:733:__init__] Config mesh_device None world_size = 16 /mnt/home/williamchen/espnet/espnet2/train/deepspeed_trainer.py:240: InstrumentationWarning: @typechecked only supports instrumenting functions wrapped with @classmethod, @staticmethod or @property -- not typechecking espnet2.train.deepspeed_trainer.DeepSpeedTrainer.valid_one_epoch def valid_one_epoch( cnode7-009:270311:270311 [3] NCCL INFO cudaDriverVersion 12020 cnode7-009:270311:270311 [3] NCCL INFO NCCL_SOCKET_IFNAME set by environment to ^lo,docker,virbr,vmnet,vboxnet cnode7-009:270311:270311 [3] NCCL INFO Bootstrap : Using enp170s0np0:10.225.1.171<0> cnode7-009:270311:270311 [3] NCCL INFO NET/Plugin : dlerror=libnccl-net.so: cannot open shared object file: No such file or directory No plugin found (libnccl-net.so), using internal implementation cnode7-009:270309:270309 [1] NCCL INFO cudaDriverVersion 12020 cnode7-009:270309:270309 [1] NCCL INFO NCCL_SOCKET_IFNAME set by environment to ^lo,docker,virbr,vmnet,vboxnet cnode7-009:270309:270309 [1] NCCL INFO Bootstrap : Using enp170s0np0:10.225.1.171<0> cnode7-009:270309:270309 [1] NCCL INFO NET/Plugin : dlerror=libnccl-net.so: cannot open shared object file: No such file or directory No plugin found (libnccl-net.so), using internal implementation [2024-12-10 08:39:51,044] [INFO] [comm.py:652:init_distributed] cdb=None [2024-12-10 08:39:51,048] [INFO] [config.py:733:__init__] Config mesh_device None world_size = 16 /mnt/home/williamchen/espnet/espnet2/train/deepspeed_trainer.py:240: InstrumentationWarning: @typechecked only supports instrumenting functions wrapped with @classmethod, @staticmethod or @property -- not typechecking espnet2.train.deepspeed_trainer.DeepSpeedTrainer.valid_one_epoch def valid_one_epoch( /mnt/home/williamchen/espnet/espnet2/train/deepspeed_trainer.py:240: InstrumentationWarning: @typechecked only supports instrumenting functions wrapped with @classmethod, @staticmethod or @property -- not typechecking espnet2.train.deepspeed_trainer.DeepSpeedTrainer.valid_one_epoch def valid_one_epoch( [2024-12-10 08:39:51,149] [INFO] [comm.py:652:init_distributed] cdb=None [2024-12-10 08:39:51,151] [INFO] [config.py:733:__init__] Config mesh_device None world_size = 16 cnode7-009:270314:270314 [6] NCCL INFO cudaDriverVersion 12020 cnode7-009:270314:270314 [6] NCCL INFO NCCL_SOCKET_IFNAME set by environment to ^lo,docker,virbr,vmnet,vboxnet cnode7-009:270314:270314 [6] NCCL INFO Bootstrap : Using enp170s0np0:10.225.1.171<0> cnode7-009:270314:270314 [6] NCCL INFO NET/Plugin : dlerror=libnccl-net.so: cannot open shared object file: No such file or directory No plugin found (libnccl-net.so), using internal implementation cnode7-009:270308:270308 [0] NCCL INFO cudaDriverVersion 12020 cnode7-009:270308:270308 [0] NCCL INFO NCCL_SOCKET_IFNAME set by environment to ^lo,docker,virbr,vmnet,vboxnet cnode7-009:270308:270308 [0] NCCL INFO Bootstrap : Using enp170s0np0:10.225.1.171<0> cnode7-009:270308:270308 [0] NCCL INFO NET/Plugin : dlerror=libnccl-net.so: cannot open shared object file: No such file or directory No plugin found (libnccl-net.so), using internal implementation [2024-12-10 08:39:51,297] [INFO] [comm.py:652:init_distributed] cdb=None [2024-12-10 08:39:51,299] [INFO] [comm.py:652:init_distributed] cdb=None cnode7-009:270314:271132 [6] NCCL INFO NCCL_SOCKET_IFNAME set by environment to ^lo,docker,virbr,vmnet,vboxnet [2024-12-10 08:39:51,307] [INFO] [config.py:733:__init__] Config mesh_device None world_size = 16 [2024-12-10 08:39:51,307] [INFO] [config.py:733:__init__] Config mesh_device None world_size = 16 cnode7-009:270311:271117 [3] NCCL INFO NCCL_SOCKET_IFNAME set by environment to ^lo,docker,virbr,vmnet,vboxnet cnode7-009:270309:271118 [1] NCCL INFO NCCL_SOCKET_IFNAME set by environment to ^lo,docker,virbr,vmnet,vboxnet cnode7-009:270314:271132 [6] NCCL INFO NET/IB : Using [0]mlx5_0:1/IB [1]mlx5_3:1/IB [2]mlx5_4:1/IB [3]mlx5_5:1/IB [4]mlx5_6:1/IB [5]mlx5_7:1/RoCE [6]mlx5_8:1/IB [7]mlx5_9:1/IB [8]mlx5_10:1/IB [RO]; OOB enp170s0np0:10.225.1.171<0> cnode7-009:270314:271132 [6] NCCL INFO Using non-device net plugin version 0 cnode7-009:270314:271132 [6] NCCL INFO Using network IB cnode7-009:270311:271117 [3] NCCL INFO NET/IB : Using [0]mlx5_0:1/IB [1]mlx5_3:1/IB [2]mlx5_4:1/IB [3]mlx5_5:1/IB [4]mlx5_6:1/IB [5]mlx5_7:1/RoCE [6]mlx5_8:1/IB [7]mlx5_9:1/IB [8]mlx5_10:1/IB [RO]; OOB enp170s0np0:10.225.1.171<0> cnode7-009:270311:271117 [3] NCCL INFO Using non-device net plugin version 0 cnode7-009:270311:271117 [3] NCCL INFO Using network IB cnode7-009:270309:271118 [1] NCCL INFO NET/IB : Using [0]mlx5_0:1/IB [1]mlx5_3:1/IB [2]mlx5_4:1/IB [3]mlx5_5:1/IB [4]mlx5_6:1/IB [5]mlx5_7:1/RoCE [6]mlx5_8:1/IB [7]mlx5_9:1/IB [8]mlx5_10:1/IB [RO]; OOB enp170s0np0:10.225.1.171<0> cnode7-009:270309:271118 [1] NCCL INFO Using non-device net plugin version 0 cnode7-009:270309:271118 [1] NCCL INFO Using network IB cnode7-009:270315:270315 [7] NCCL INFO cudaDriverVersion 12020 cnode7-009:270315:270315 [7] NCCL INFO NCCL_SOCKET_IFNAME set by environment to ^lo,docker,virbr,vmnet,vboxnet cnode7-009:270315:270315 [7] NCCL INFO Bootstrap : Using enp170s0np0:10.225.1.171<0> cnode7-009:270315:270315 [7] NCCL INFO NET/Plugin : dlerror=libnccl-net.so: cannot open shared object file: No such file or directory No plugin found (libnccl-net.so), using internal implementation cnode7-009:270308:271135 [0] NCCL INFO NCCL_SOCKET_IFNAME set by environment to ^lo,docker,virbr,vmnet,vboxnet cnode7-009:270313:270313 [5] NCCL INFO cudaDriverVersion 12020 cnode7-009:270313:270313 [5] NCCL INFO NCCL_SOCKET_IFNAME set by environment to ^lo,docker,virbr,vmnet,vboxnet cnode7-009:270313:270313 [5] NCCL INFO Bootstrap : Using enp170s0np0:10.225.1.171<0> cnode7-009:270313:270313 [5] NCCL INFO NET/Plugin : dlerror=libnccl-net.so: cannot open shared object file: No such file or directory No plugin found (libnccl-net.so), using internal implementation cnode7-009:270308:271135 [0] NCCL INFO NET/IB : Using [0]mlx5_0:1/IB [1]mlx5_3:1/IB [2]mlx5_4:1/IB [3]mlx5_5:1/IB [4]mlx5_6:1/IB [5]mlx5_7:1/RoCE [6]mlx5_8:1/IB [7]mlx5_9:1/IB [8]mlx5_10:1/IB [RO]; OOB enp170s0np0:10.225.1.171<0> cnode7-009:270308:271135 [0] NCCL INFO Using non-device net plugin version 0 cnode7-009:270308:271135 [0] NCCL INFO Using network IB /mnt/home/williamchen/espnet/espnet2/train/deepspeed_trainer.py:240: InstrumentationWarning: @typechecked only supports instrumenting functions wrapped with @classmethod, @staticmethod or @property -- not typechecking espnet2.train.deepspeed_trainer.DeepSpeedTrainer.valid_one_epoch def valid_one_epoch( /mnt/home/williamchen/espnet/espnet2/train/deepspeed_trainer.py:240: InstrumentationWarning: @typechecked only supports instrumenting functions wrapped with @classmethod, @staticmethod or @property -- not typechecking espnet2.train.deepspeed_trainer.DeepSpeedTrainer.valid_one_epoch def valid_one_epoch( [2024-12-10 08:39:52,100] [INFO] [comm.py:652:init_distributed] cdb=None [2024-12-10 08:39:52,102] [INFO] [config.py:733:__init__] Config mesh_device None world_size = 16 [2024-12-10 08:39:52,124] [INFO] [comm.py:652:init_distributed] cdb=None [2024-12-10 08:39:52,126] [INFO] [config.py:733:__init__] Config mesh_device None world_size = 16 cnode7-009:270313:271171 [5] NCCL INFO NCCL_SOCKET_IFNAME set by environment to ^lo,docker,virbr,vmnet,vboxnet cnode7-009:270315:271168 [7] NCCL INFO NCCL_SOCKET_IFNAME set by environment to ^lo,docker,virbr,vmnet,vboxnet cnode7-009:270312:270312 [4] NCCL INFO cudaDriverVersion 12020 cnode7-009:270312:270312 [4] NCCL INFO NCCL_SOCKET_IFNAME set by environment to ^lo,docker,virbr,vmnet,vboxnet cnode7-009:270312:270312 [4] NCCL INFO Bootstrap : Using enp170s0np0:10.225.1.171<0> cnode7-009:270312:270312 [4] NCCL INFO NET/Plugin : dlerror=libnccl-net.so: cannot open shared object file: No such file or directory No plugin found (libnccl-net.so), using internal implementation cnode7-009:270313:271171 [5] NCCL INFO NET/IB : Using [0]mlx5_0:1/IB [1]mlx5_3:1/IB [2]mlx5_4:1/IB [3]mlx5_5:1/IB [4]mlx5_6:1/IB [5]mlx5_7:1/RoCE [6]mlx5_8:1/IB [7]mlx5_9:1/IB [8]mlx5_10:1/IB [RO]; OOB enp170s0np0:10.225.1.171<0> cnode7-009:270313:271171 [5] NCCL INFO Using non-device net plugin version 0 cnode7-009:270313:271171 [5] NCCL INFO Using network IB cnode7-009:270315:271168 [7] NCCL INFO NET/IB : Using [0]mlx5_0:1/IB [1]mlx5_3:1/IB [2]mlx5_4:1/IB [3]mlx5_5:1/IB [4]mlx5_6:1/IB [5]mlx5_7:1/RoCE [6]mlx5_8:1/IB [7]mlx5_9:1/IB [8]mlx5_10:1/IB [RO]; OOB enp170s0np0:10.225.1.171<0> cnode7-009:270315:271168 [7] NCCL INFO Using non-device net plugin version 0 cnode7-009:270315:271168 [7] NCCL INFO Using network IB cnode7-009:270310:270310 [2] NCCL INFO cudaDriverVersion 12020 cnode7-009:270310:270310 [2] NCCL INFO NCCL_SOCKET_IFNAME set by environment to ^lo,docker,virbr,vmnet,vboxnet cnode7-009:270310:270310 [2] NCCL INFO Bootstrap : Using enp170s0np0:10.225.1.171<0> cnode7-009:270310:270310 [2] NCCL INFO NET/Plugin : dlerror=libnccl-net.so: cannot open shared object file: No such file or directory No plugin found (libnccl-net.so), using internal implementation cnode7-009:270312:271209 [4] NCCL INFO NCCL_SOCKET_IFNAME set by environment to ^lo,docker,virbr,vmnet,vboxnet cnode7-009:270310:271224 [2] NCCL INFO NCCL_SOCKET_IFNAME set by environment to ^lo,docker,virbr,vmnet,vboxnet cnode7-009:270310:271224 [2] NCCL INFO NET/IB : Using [0]mlx5_0:1/IB [1]mlx5_3:1/IB [2]mlx5_4:1/IB [3]mlx5_5:1/IB [4]mlx5_6:1/IB [5]mlx5_7:1/RoCE [6]mlx5_8:1/IB [7]mlx5_9:1/IB [8]mlx5_10:1/IB [RO]; OOB enp170s0np0:10.225.1.171<0> cnode7-009:270310:271224 [2] NCCL INFO Using non-device net plugin version 0 cnode7-009:270310:271224 [2] NCCL INFO Using network IB cnode7-009:270312:271209 [4] NCCL INFO NET/IB : Using [0]mlx5_0:1/IB [1]mlx5_3:1/IB [2]mlx5_4:1/IB [3]mlx5_5:1/IB [4]mlx5_6:1/IB [5]mlx5_7:1/RoCE [6]mlx5_8:1/IB [7]mlx5_9:1/IB [8]mlx5_10:1/IB [RO]; OOB enp170s0np0:10.225.1.171<0> cnode7-009:270312:271209 [4] NCCL INFO Using non-device net plugin version 0 cnode7-009:270312:271209 [4] NCCL INFO Using network IB cnode7-009:270311:271117 [3] NCCL INFO comm 0x555569a227f0 rank 11 nranks 16 cudaDev 3 nvmlDev 3 busId 61000 commId 0xe3295ea1839cefc9 - Init START cnode7-009:270309:271118 [1] NCCL INFO comm 0x55558161ad80 rank 9 nranks 16 cudaDev 1 nvmlDev 1 busId 43000 commId 0xe3295ea1839cefc9 - Init START cnode7-008:628125:628997 [2] NCCL INFO comm 0x55557c41cde0 rank 2 nranks 16 cudaDev 2 nvmlDev 2 busId 52000 commId 0xe3295ea1839cefc9 - Init START cnode7-009:270308:271135 [0] NCCL INFO comm 0x555563d3b5b0 rank 8 nranks 16 cudaDev 0 nvmlDev 0 busId 1b000 commId 0xe3295ea1839cefc9 - Init START cnode7-008:628124:628983 [1] NCCL INFO comm 0x55557c01e980 rank 1 nranks 16 cudaDev 1 nvmlDev 1 busId 43000 commId 0xe3295ea1839cefc9 - Init START cnode7-008:628123:628980 [0] NCCL INFO comm 0x5555647681e0 rank 0 nranks 16 cudaDev 0 nvmlDev 0 busId 1b000 commId 0xe3295ea1839cefc9 - Init START cnode7-009:270310:271224 [2] NCCL INFO comm 0x555560a14700 rank 10 nranks 16 cudaDev 2 nvmlDev 2 busId 52000 commId 0xe3295ea1839cefc9 - Init START cnode7-008:628130:628985 [7] NCCL INFO comm 0x55556ca1b270 rank 7 nranks 16 cudaDev 7 nvmlDev 7 busId df000 commId 0xe3295ea1839cefc9 - Init START cnode7-008:628128:628988 [5] NCCL INFO comm 0x555575c23df0 rank 5 nranks 16 cudaDev 5 nvmlDev 5 busId c3000 commId 0xe3295ea1839cefc9 - Init START cnode7-009:270313:271171 [5] NCCL INFO comm 0x555560c1ad60 rank 13 nranks 16 cudaDev 5 nvmlDev 5 busId c3000 commId 0xe3295ea1839cefc9 - Init START cnode7-008:628127:628996 [4] NCCL INFO comm 0x55558101ada0 rank 4 nranks 16 cudaDev 4 nvmlDev 4 busId 9d000 commId 0xe3295ea1839cefc9 - Init START cnode7-008:628126:628984 [3] NCCL INFO comm 0x555566a1a9d0 rank 3 nranks 16 cudaDev 3 nvmlDev 3 busId 61000 commId 0xe3295ea1839cefc9 - Init START cnode7-008:628129:628991 [6] NCCL INFO comm 0x55557501a8c0 rank 6 nranks 16 cudaDev 6 nvmlDev 6 busId d1000 commId 0xe3295ea1839cefc9 - Init START cnode7-009:270315:271168 [7] NCCL INFO comm 0x555561a1aca0 rank 15 nranks 16 cudaDev 7 nvmlDev 7 busId df000 commId 0xe3295ea1839cefc9 - Init START cnode7-009:270314:271132 [6] NCCL INFO comm 0x55557bc1ae80 rank 14 nranks 16 cudaDev 6 nvmlDev 6 busId d1000 commId 0xe3295ea1839cefc9 - Init START cnode7-009:270312:271209 [4] NCCL INFO comm 0x55557261ed20 rank 12 nranks 16 cudaDev 4 nvmlDev 4 busId 9d000 commId 0xe3295ea1839cefc9 - Init START cnode7-008:628123:628980 [0] NCCL INFO Setting affinity for GPU 0 to ff,ffffffff,ffff0000,00000000,00ffffff,ffffffff cnode7-008:628123:628980 [0] NCCL INFO NVLS multicast support is available on dev 0 cnode7-008:628130:628985 [7] NCCL INFO Setting affinity for GPU 7 to ffffffff,ffffff00,00000000,0000ffff,ffffffff,ff000000,00000000 cnode7-008:628130:628985 [7] NCCL INFO NVLS multicast support is available on dev 7 cnode7-008:628127:628996 [4] NCCL INFO Setting affinity for GPU 4 to ffffffff,ffffff00,00000000,0000ffff,ffffffff,ff000000,00000000 cnode7-008:628127:628996 [4] NCCL INFO NVLS multicast support is available on dev 4 cnode7-008:628126:628984 [3] NCCL INFO Setting affinity for GPU 3 to ff,ffffffff,ffff0000,00000000,00ffffff,ffffffff cnode7-008:628126:628984 [3] NCCL INFO NVLS multicast support is available on dev 3 cnode7-008:628129:628991 [6] NCCL INFO Setting affinity for GPU 6 to ffffffff,ffffff00,00000000,0000ffff,ffffffff,ff000000,00000000 cnode7-008:628129:628991 [6] NCCL INFO NVLS multicast support is available on dev 6 cnode7-008:628125:628997 [2] NCCL INFO Setting affinity for GPU 2 to ff,ffffffff,ffff0000,00000000,00ffffff,ffffffff cnode7-008:628125:628997 [2] NCCL INFO NVLS multicast support is available on dev 2 cnode7-008:628124:628983 [1] NCCL INFO Setting affinity for GPU 1 to ff,ffffffff,ffff0000,00000000,00ffffff,ffffffff cnode7-008:628124:628983 [1] NCCL INFO NVLS multicast support is available on dev 1 cnode7-008:628128:628988 [5] NCCL INFO Setting affinity for GPU 5 to ffffffff,ffffff00,00000000,0000ffff,ffffffff,ff000000,00000000 cnode7-008:628128:628988 [5] NCCL INFO NVLS multicast support is available on dev 5 cnode7-009:270311:271117 [3] NCCL INFO Setting affinity for GPU 3 to ff,ffffffff,ffff0000,00000000,00ffffff,ffffffff cnode7-009:270311:271117 [3] NCCL INFO NVLS multicast support is available on dev 3 cnode7-009:270309:271118 [1] NCCL INFO Setting affinity for GPU 1 to ff,ffffffff,ffff0000,00000000,00ffffff,ffffffff cnode7-009:270309:271118 [1] NCCL INFO NVLS multicast support is available on dev 1 cnode7-009:270308:271135 [0] NCCL INFO Setting affinity for GPU 0 to ff,ffffffff,ffff0000,00000000,00ffffff,ffffffff cnode7-009:270308:271135 [0] NCCL INFO NVLS multicast support is available on dev 0 cnode7-009:270310:271224 [2] NCCL INFO Setting affinity for GPU 2 to ff,ffffffff,ffff0000,00000000,00ffffff,ffffffff cnode7-009:270310:271224 [2] NCCL INFO NVLS multicast support is available on dev 2 cnode7-009:270313:271171 [5] NCCL INFO Setting affinity for GPU 5 to ffffffff,ffffff00,00000000,0000ffff,ffffffff,ff000000,00000000 cnode7-009:270313:271171 [5] NCCL INFO NVLS multicast support is available on dev 5 cnode7-008:628128:628988 [5] NCCL INFO comm 0x555575c23df0 rank 5 nRanks 16 nNodes 2 localRanks 8 localRank 5 MNNVL 0 cnode7-008:628128:628988 [5] NCCL INFO NVLS Head 0: 0 8 cnode7-008:628128:628988 [5] NCCL INFO NVLS Head 1: 1 9 cnode7-008:628128:628988 [5] NCCL INFO NVLS Head 2: 2 10 cnode7-008:628128:628988 [5] NCCL INFO NVLS Head 3: 3 11 cnode7-008:628128:628988 [5] NCCL INFO NVLS Head 4: 4 12 cnode7-008:628128:628988 [5] NCCL INFO NVLS Head 5: 5 13 cnode7-008:628128:628988 [5] NCCL INFO NVLS Head 6: 6 14 cnode7-008:628128:628988 [5] NCCL INFO NVLS Head 7: 7 15 cnode7-008:628128:628988 [5] NCCL INFO Trees [0] 6/-1/-1->5->4 [1] 6/-1/-1->5->4 [2] 6/-1/-1->5->4 [3] 6/-1/-1->5->4 [4] 6/-1/-1->5->4 [5] 6/13/-1->5->-1 [6] -1/-1/-1->5->4 [7] 6/-1/-1->5->4 [8] 6/-1/-1->5->4 [9] 6/-1/-1->5->4 [10] 6/-1/-1->5->4 [11] 6/-1/-1->5->4 [12] 6/-1/-1->5->4 [13] 6/-1/-1->5->13 [14] -1/-1/-1->5->4 [15] 6/-1/-1->5->4 cnode7-008:628128:628988 [5] NCCL INFO P2P Chunksize set to 131072 cnode7-009:270309:271118 [1] NCCL INFO comm 0x55558161ad80 rank 9 nRanks 16 nNodes 2 localRanks 8 localRank 1 MNNVL 0 cnode7-009:270309:271118 [1] NCCL INFO Trees [0] 10/-1/-1->9->8 [1] 10/-1/-1->9->1 [2] -1/-1/-1->9->8 [3] 10/-1/-1->9->8 [4] 10/-1/-1->9->8 [5] 10/-1/-1->9->8 [6] 10/-1/-1->9->8 [7] 10/-1/-1->9->8 [8] 10/-1/-1->9->8 [9] 10/1/-1->9->-1 [10] -1/-1/-1->9->8 [11] 10/-1/-1->9->8 [12] 10/-1/-1->9->8 [13] 10/-1/-1->9->8 [14] 10/-1/-1->9->8 [15] 10/-1/-1->9->8 cnode7-009:270309:271118 [1] NCCL INFO P2P Chunksize set to 131072 cnode7-009:270308:271135 [0] NCCL INFO comm 0x555563d3b5b0 rank 8 nRanks 16 nNodes 2 localRanks 8 localRank 0 MNNVL 0 cnode7-009:270308:271135 [0] NCCL INFO Trees [0] 9/-1/-1->8->0 [1] -1/-1/-1->8->15 [2] 9/-1/-1->8->15 [3] 9/-1/-1->8->15 [4] 9/-1/-1->8->15 [5] 9/-1/-1->8->15 [6] 9/-1/-1->8->15 [7] 9/-1/-1->8->15 [8] 9/0/-1->8->-1 [9] -1/-1/-1->8->15 [10] 9/-1/-1->8->15 [11] 9/-1/-1->8->15 [12] 9/-1/-1->8->15 [13] 9/-1/-1->8->15 [14] 9/-1/-1->8->15 [15] 9/-1/-1->8->15 cnode7-009:270308:271135 [0] NCCL INFO P2P Chunksize set to 131072 cnode7-008:628124:628983 [1] NCCL INFO comm 0x55557c01e980 rank 1 nRanks 16 nNodes 2 localRanks 8 localRank 1 MNNVL 0 cnode7-008:628124:628983 [1] NCCL INFO NVLS Head 0: 0 8 cnode7-008:628124:628983 [1] NCCL INFO NVLS Head 1: 1 9 cnode7-008:628124:628983 [1] NCCL INFO NVLS Head 2: 2 10 cnode7-008:628124:628983 [1] NCCL INFO NVLS Head 3: 3 11 cnode7-008:628124:628983 [1] NCCL INFO NVLS Head 4: 4 12 cnode7-008:628124:628983 [1] NCCL INFO NVLS Head 5: 5 13 cnode7-008:628124:628983 [1] NCCL INFO NVLS Head 6: 6 14 cnode7-008:628124:628983 [1] NCCL INFO NVLS Head 7: 7 15 cnode7-008:628124:628983 [1] NCCL INFO Trees [0] 2/-1/-1->1->0 [1] 2/9/-1->1->-1 [2] -1/-1/-1->1->0 [3] 2/-1/-1->1->0 [4] 2/-1/-1->1->0 [5] 2/-1/-1->1->0 [6] 2/-1/-1->1->0 [7] 2/-1/-1->1->0 [8] 2/-1/-1->1->0 [9] 2/-1/-1->1->9 [10] -1/-1/-1->1->0 [11] 2/-1/-1->1->0 [12] 2/-1/-1->1->0 [13] 2/-1/-1->1->0 [14] 2/-1/-1->1->0 [15] 2/-1/-1->1->0 cnode7-008:628124:628983 [1] NCCL INFO P2P Chunksize set to 131072 cnode7-009:270312:271209 [4] NCCL INFO Setting affinity for GPU 4 to ffffffff,ffffff00,00000000,0000ffff,ffffffff,ff000000,00000000 cnode7-009:270312:271209 [4] NCCL INFO NVLS multicast support is available on dev 4 cnode7-009:270312:271209 [4] NCCL INFO comm 0x55557261ed20 rank 12 nRanks 16 nNodes 2 localRanks 8 localRank 4 MNNVL 0 cnode7-009:270312:271209 [4] NCCL INFO Trees [0] 13/-1/-1->12->11 [1] 13/-1/-1->12->11 [2] 13/-1/-1->12->11 [3] 13/-1/-1->12->11 [4] 13/-1/-1->12->4 [5] -1/-1/-1->12->11 [6] 13/-1/-1->12->11 [7] 13/-1/-1->12->11 [8] 13/-1/-1->12->11 [9] 13/-1/-1->12->11 [10] 13/-1/-1->12->11 [11] 13/-1/-1->12->11 [12] 13/4/-1->12->-1 [13] -1/-1/-1->12->11 [14] 13/-1/-1->12->11 [15] 13/-1/-1->12->11 cnode7-009:270312:271209 [4] NCCL INFO P2P Chunksize set to 131072 cnode7-008:628123:628980 [0] NCCL INFO comm 0x5555647681e0 rank 0 nRanks 16 nNodes 2 localRanks 8 localRank 0 MNNVL 0 cnode7-008:628123:628980 [0] NCCL INFO NVLS Head 0: 0 8 cnode7-008:628123:628980 [0] NCCL INFO NVLS Head 1: 1 9 cnode7-008:628123:628980 [0] NCCL INFO NVLS Head 2: 2 10 cnode7-008:628123:628980 [0] NCCL INFO NVLS Head 3: 3 11 cnode7-008:628123:628980 [0] NCCL INFO NVLS Head 4: 4 12 cnode7-008:628123:628980 [0] NCCL INFO NVLS Head 5: 5 13 cnode7-008:628123:628980 [0] NCCL INFO NVLS Head 6: 6 14 cnode7-008:628123:628980 [0] NCCL INFO NVLS Head 7: 7 15 cnode7-008:628123:628980 [0] NCCL INFO Channel 00/16 : 0 7 6 5 4 3 2 1 9 10 11 12 13 14 15 8 cnode7-008:628123:628980 [0] NCCL INFO Channel 01/16 : 0 8 15 14 13 12 11 10 9 1 2 3 4 5 6 7 cnode7-008:628123:628980 [0] NCCL INFO Channel 02/16 : 0 7 6 5 4 3 11 12 13 14 15 8 9 10 2 1 cnode7-008:628123:628980 [0] NCCL INFO Channel 03/16 : 0 1 2 10 9 8 15 14 13 12 11 3 4 5 6 7 cnode7-008:628123:628980 [0] NCCL INFO Channel 04/16 : 0 7 6 5 13 14 15 8 9 10 11 12 4 3 2 1 cnode7-008:628123:628980 [0] NCCL INFO Channel 05/16 : 0 1 2 3 4 12 11 10 9 8 15 14 13 5 6 7 cnode7-008:628123:628980 [0] NCCL INFO Channel 06/16 : 0 7 15 8 9 10 11 12 13 14 6 5 4 3 2 1 cnode7-008:628123:628980 [0] NCCL INFO Channel 07/16 : 0 1 2 3 4 5 6 14 13 12 11 10 9 8 15 7 cnode7-008:628123:628980 [0] NCCL INFO Channel 08/16 : 0 7 6 5 4 3 2 1 9 10 11 12 13 14 15 8 cnode7-008:628123:628980 [0] NCCL INFO Channel 09/16 : 0 8 15 14 13 12 11 10 9 1 2 3 4 5 6 7 cnode7-008:628123:628980 [0] NCCL INFO Channel 10/16 : 0 7 6 5 4 3 11 12 13 14 15 8 9 10 2 1 cnode7-009:270315:271168 [7] NCCL INFO Setting affinity for GPU 7 to ffffffff,ffffff00,00000000,0000ffff,ffffffff,ff000000,00000000 cnode7-009:270315:271168 [7] NCCL INFO NVLS multicast support is available on dev 7 cnode7-009:270315:271168 [7] NCCL INFO comm 0x555561a1aca0 rank 15 nRanks 16 nNodes 2 localRanks 8 localRank 7 MNNVL 0 cnode7-009:270315:271168 [7] NCCL INFO Trees [0] -1/-1/-1->15->14 [1] 8/-1/-1->15->14 [2] 8/-1/-1->15->14 [3] 8/-1/-1->15->14 [4] 8/-1/-1->15->14 [5] 8/-1/-1->15->14 [6] 8/-1/-1->15->14 [7] 8/-1/-1->15->7 [8] -1/-1/-1->15->14 [9] 8/-1/-1->15->14 [10] 8/-1/-1->15->14 [11] 8/-1/-1->15->14 [12] 8/-1/-1->15->14 [13] 8/-1/-1->15->14 [14] 8/-1/-1->15->14 [15] 8/7/-1->15->-1 cnode7-009:270315:271168 [7] NCCL INFO P2P Chunksize set to 131072 cnode7-008:628123:628980 [0] NCCL INFO Channel 11/16 : 0 1 2 10 9 8 15 14 13 12 11 3 4 5 6 7 cnode7-008:628123:628980 [0] NCCL INFO Channel 12/16 : 0 7 6 5 13 14 15 8 9 10 11 12 4 3 2 1 cnode7-008:628123:628980 [0] NCCL INFO Channel 13/16 : 0 1 2 3 4 12 11 10 9 8 15 14 13 5 6 7 cnode7-008:628123:628980 [0] NCCL INFO Channel 14/16 : 0 7 15 8 9 10 11 12 13 14 6 5 4 3 2 1 cnode7-008:628123:628980 [0] NCCL INFO Channel 15/16 : 0 1 2 3 4 5 6 14 13 12 11 10 9 8 15 7 cnode7-008:628123:628980 [0] NCCL INFO Trees [0] 1/8/-1->0->-1 [1] -1/-1/-1->0->7 [2] 1/-1/-1->0->7 [3] 1/-1/-1->0->7 [4] 1/-1/-1->0->7 [5] 1/-1/-1->0->7 [6] 1/-1/-1->0->7 [7] 1/-1/-1->0->7 [8] 1/-1/-1->0->8 [9] -1/-1/-1->0->7 [10] 1/-1/-1->0->7 [11] 1/-1/-1->0->7 [12] 1/-1/-1->0->7 [13] 1/-1/-1->0->7 [14] 1/-1/-1->0->7 [15] 1/-1/-1->0->7 cnode7-008:628123:628980 [0] NCCL INFO P2P Chunksize set to 131072 cnode7-008:628126:628984 [3] NCCL INFO comm 0x555566a1a9d0 rank 3 nRanks 16 nNodes 2 localRanks 8 localRank 3 MNNVL 0 cnode7-008:628126:628984 [3] NCCL INFO NVLS Head 0: 0 8 cnode7-008:628126:628984 [3] NCCL INFO NVLS Head 1: 1 9 cnode7-008:628126:628984 [3] NCCL INFO NVLS Head 2: 2 10 cnode7-008:628126:628984 [3] NCCL INFO NVLS Head 3: 3 11 cnode7-008:628126:628984 [3] NCCL INFO NVLS Head 4: 4 12 cnode7-008:628126:628984 [3] NCCL INFO NVLS Head 5: 5 13 cnode7-008:628126:628984 [3] NCCL INFO NVLS Head 6: 6 14 cnode7-008:628126:628984 [3] NCCL INFO NVLS Head 7: 7 15 cnode7-008:628126:628984 [3] NCCL INFO Trees [0] 4/-1/-1->3->2 [1] 4/-1/-1->3->2 [2] 4/-1/-1->3->2 [3] 4/11/-1->3->-1 [4] -1/-1/-1->3->2 [5] 4/-1/-1->3->2 [6] 4/-1/-1->3->2 [7] 4/-1/-1->3->2 [8] 4/-1/-1->3->2 [9] 4/-1/-1->3->2 [10] 4/-1/-1->3->2 [11] 4/-1/-1->3->11 [12] -1/-1/-1->3->2 [13] 4/-1/-1->3->2 [14] 4/-1/-1->3->2 [15] 4/-1/-1->3->2 cnode7-008:628126:628984 [3] NCCL INFO P2P Chunksize set to 131072 cnode7-009:270311:271117 [3] NCCL INFO comm 0x555569a227f0 rank 11 nRanks 16 nNodes 2 localRanks 8 localRank 3 MNNVL 0 cnode7-009:270311:271117 [3] NCCL INFO Trees [0] 12/-1/-1->11->10 [1] 12/-1/-1->11->10 [2] 12/-1/-1->11->10 [3] 12/-1/-1->11->3 [4] -1/-1/-1->11->10 [5] 12/-1/-1->11->10 [6] 12/-1/-1->11->10 [7] 12/-1/-1->11->10 [8] 12/-1/-1->11->10 [9] 12/-1/-1->11->10 [10] 12/-1/-1->11->10 [11] 12/3/-1->11->-1 [12] -1/-1/-1->11->10 [13] 12/-1/-1->11->10 [14] 12/-1/-1->11->10 [15] 12/-1/-1->11->10 cnode7-009:270311:271117 [3] NCCL INFO P2P Chunksize set to 131072 cnode7-008:628125:628997 [2] NCCL INFO comm 0x55557c41cde0 rank 2 nRanks 16 nNodes 2 localRanks 8 localRank 2 MNNVL 0 cnode7-008:628125:628997 [2] NCCL INFO NVLS Head 0: 0 8 cnode7-008:628125:628997 [2] NCCL INFO NVLS Head 1: 1 9 cnode7-008:628125:628997 [2] NCCL INFO NVLS Head 2: 2 10 cnode7-008:628125:628997 [2] NCCL INFO NVLS Head 3: 3 11 cnode7-008:628125:628997 [2] NCCL INFO NVLS Head 4: 4 12 cnode7-008:628125:628997 [2] NCCL INFO NVLS Head 5: 5 13 cnode7-008:628125:628997 [2] NCCL INFO NVLS Head 6: 6 14 cnode7-008:628125:628997 [2] NCCL INFO NVLS Head 7: 7 15 cnode7-008:628125:628997 [2] NCCL INFO Trees [0] 3/-1/-1->2->1 [1] 3/-1/-1->2->1 [2] 3/10/-1->2->-1 [3] -1/-1/-1->2->1 [4] 3/-1/-1->2->1 [5] 3/-1/-1->2->1 [6] 3/-1/-1->2->1 [7] 3/-1/-1->2->1 [8] 3/-1/-1->2->1 [9] 3/-1/-1->2->1 [10] 3/-1/-1->2->10 [11] -1/-1/-1->2->1 [12] 3/-1/-1->2->1 [13] 3/-1/-1->2->1 [14] 3/-1/-1->2->1 [15] 3/-1/-1->2->1 cnode7-008:628125:628997 [2] NCCL INFO P2P Chunksize set to 131072 cnode7-008:628127:628996 [4] NCCL INFO comm 0x55558101ada0 rank 4 nRanks 16 nNodes 2 localRanks 8 localRank 4 MNNVL 0 cnode7-008:628127:628996 [4] NCCL INFO NVLS Head 0: 0 8 cnode7-008:628127:628996 [4] NCCL INFO NVLS Head 1: 1 9 cnode7-008:628127:628996 [4] NCCL INFO NVLS Head 2: 2 10 cnode7-008:628127:628996 [4] NCCL INFO NVLS Head 3: 3 11 cnode7-008:628127:628996 [4] NCCL INFO NVLS Head 4: 4 12 cnode7-008:628127:628996 [4] NCCL INFO NVLS Head 5: 5 13 cnode7-008:628127:628996 [4] NCCL INFO NVLS Head 6: 6 14 cnode7-008:628127:628996 [4] NCCL INFO NVLS Head 7: 7 15 cnode7-008:628127:628996 [4] NCCL INFO Trees [0] 5/-1/-1->4->3 [1] 5/-1/-1->4->3 [2] 5/-1/-1->4->3 [3] 5/-1/-1->4->3 [4] 5/12/-1->4->-1 [5] -1/-1/-1->4->3 [6] 5/-1/-1->4->3 [7] 5/-1/-1->4->3 [8] 5/-1/-1->4->3 [9] 5/-1/-1->4->3 [10] 5/-1/-1->4->3 [11] 5/-1/-1->4->3 [12] 5/-1/-1->4->12 [13] -1/-1/-1->4->3 [14] 5/-1/-1->4->3 [15] 5/-1/-1->4->3 cnode7-008:628127:628996 [4] NCCL INFO P2P Chunksize set to 131072 cnode7-009:270310:271224 [2] NCCL INFO comm 0x555560a14700 rank 10 nRanks 16 nNodes 2 localRanks 8 localRank 2 MNNVL 0 cnode7-009:270310:271224 [2] NCCL INFO Trees [0] 11/-1/-1->10->9 [1] 11/-1/-1->10->9 [2] 11/-1/-1->10->2 [3] -1/-1/-1->10->9 [4] 11/-1/-1->10->9 [5] 11/-1/-1->10->9 [6] 11/-1/-1->10->9 [7] 11/-1/-1->10->9 [8] 11/-1/-1->10->9 [9] 11/-1/-1->10->9 [10] 11/2/-1->10->-1 [11] -1/-1/-1->10->9 [12] 11/-1/-1->10->9 [13] 11/-1/-1->10->9 [14] 11/-1/-1->10->9 [15] 11/-1/-1->10->9 cnode7-009:270310:271224 [2] NCCL INFO P2P Chunksize set to 131072 cnode7-009:270314:271132 [6] NCCL INFO Setting affinity for GPU 6 to ffffffff,ffffff00,00000000,0000ffff,ffffffff,ff000000,00000000 cnode7-009:270314:271132 [6] NCCL INFO NVLS multicast support is available on dev 6 cnode7-009:270314:271132 [6] NCCL INFO comm 0x55557bc1ae80 rank 14 nRanks 16 nNodes 2 localRanks 8 localRank 6 MNNVL 0 cnode7-009:270314:271132 [6] NCCL INFO Trees [0] 15/-1/-1->14->13 [1] 15/-1/-1->14->13 [2] 15/-1/-1->14->13 [3] 15/-1/-1->14->13 [4] 15/-1/-1->14->13 [5] 15/-1/-1->14->13 [6] 15/-1/-1->14->6 [7] -1/-1/-1->14->13 [8] 15/-1/-1->14->13 [9] 15/-1/-1->14->13 [10] 15/-1/-1->14->13 [11] 15/-1/-1->14->13 [12] 15/-1/-1->14->13 [13] 15/-1/-1->14->13 [14] 15/6/-1->14->-1 [15] -1/-1/-1->14->13 cnode7-009:270314:271132 [6] NCCL INFO P2P Chunksize set to 131072 cnode7-009:270313:271171 [5] NCCL INFO comm 0x555560c1ad60 rank 13 nRanks 16 nNodes 2 localRanks 8 localRank 5 MNNVL 0 cnode7-009:270313:271171 [5] NCCL INFO Trees [0] 14/-1/-1->13->12 [1] 14/-1/-1->13->12 [2] 14/-1/-1->13->12 [3] 14/-1/-1->13->12 [4] 14/-1/-1->13->12 [5] 14/-1/-1->13->5 [6] -1/-1/-1->13->12 [7] 14/-1/-1->13->12 [8] 14/-1/-1->13->12 [9] 14/-1/-1->13->12 [10] 14/-1/-1->13->12 [11] 14/-1/-1->13->12 [12] 14/-1/-1->13->12 [13] 14/5/-1->13->-1 [14] -1/-1/-1->13->12 [15] 14/-1/-1->13->12 cnode7-009:270313:271171 [5] NCCL INFO P2P Chunksize set to 131072 cnode7-009:270311:271117 [3] NCCL INFO Channel 00/0 : 11[3] -> 12[4] via P2P/CUMEM cnode7-009:270311:271117 [3] NCCL INFO Channel 02/0 : 11[3] -> 12[4] via P2P/CUMEM cnode7-009:270311:271117 [3] NCCL INFO Channel 04/0 : 11[3] -> 12[4] via P2P/CUMEM cnode7-009:270311:271117 [3] NCCL INFO Channel 06/0 : 11[3] -> 12[4] via P2P/CUMEM cnode7-009:270311:271117 [3] NCCL INFO Channel 08/0 : 11[3] -> 12[4] via P2P/CUMEM cnode7-009:270311:271117 [3] NCCL INFO Channel 10/0 : 11[3] -> 12[4] via P2P/CUMEM cnode7-009:270311:271117 [3] NCCL INFO Channel 12/0 : 11[3] -> 12[4] via P2P/CUMEM cnode7-009:270311:271117 [3] NCCL INFO Channel 14/0 : 11[3] -> 12[4] via P2P/CUMEM cnode7-008:628130:628985 [7] NCCL INFO comm 0x55556ca1b270 rank 7 nRanks 16 nNodes 2 localRanks 8 localRank 7 MNNVL 0 cnode7-008:628130:628985 [7] NCCL INFO NVLS Head 0: 0 8 cnode7-008:628130:628985 [7] NCCL INFO NVLS Head 1: 1 9 cnode7-008:628130:628985 [7] NCCL INFO NVLS Head 2: 2 10 cnode7-008:628130:628985 [7] NCCL INFO NVLS Head 3: 3 11 cnode7-008:628130:628985 [7] NCCL INFO NVLS Head 4: 4 12 cnode7-008:628130:628985 [7] NCCL INFO NVLS Head 5: 5 13 cnode7-008:628130:628985 [7] NCCL INFO NVLS Head 6: 6 14 cnode7-008:628130:628985 [7] NCCL INFO NVLS Head 7: 7 15 cnode7-008:628130:628985 [7] NCCL INFO Trees [0] -1/-1/-1->7->6 [1] 0/-1/-1->7->6 [2] 0/-1/-1->7->6 [3] 0/-1/-1->7->6 [4] 0/-1/-1->7->6 [5] 0/-1/-1->7->6 [6] 0/-1/-1->7->6 [7] 0/15/-1->7->-1 [8] -1/-1/-1->7->6 [9] 0/-1/-1->7->6 [10] 0/-1/-1->7->6 [11] 0/-1/-1->7->6 [12] 0/-1/-1->7->6 [13] 0/-1/-1->7->6 [14] 0/-1/-1->7->6 [15] 0/-1/-1->7->15 cnode7-008:628130:628985 [7] NCCL INFO P2P Chunksize set to 131072 cnode7-008:628129:628991 [6] NCCL INFO comm 0x55557501a8c0 rank 6 nRanks 16 nNodes 2 localRanks 8 localRank 6 MNNVL 0 cnode7-008:628129:628991 [6] NCCL INFO NVLS Head 0: 0 8 cnode7-008:628129:628991 [6] NCCL INFO NVLS Head 1: 1 9 cnode7-008:628129:628991 [6] NCCL INFO NVLS Head 2: 2 10 cnode7-008:628129:628991 [6] NCCL INFO NVLS Head 3: 3 11 cnode7-008:628129:628991 [6] NCCL INFO NVLS Head 4: 4 12 cnode7-008:628129:628991 [6] NCCL INFO NVLS Head 5: 5 13 cnode7-008:628129:628991 [6] NCCL INFO NVLS Head 6: 6 14 cnode7-008:628129:628991 [6] NCCL INFO NVLS Head 7: 7 15 cnode7-008:628129:628991 [6] NCCL INFO Trees [0] 7/-1/-1->6->5 [1] 7/-1/-1->6->5 [2] 7/-1/-1->6->5 [3] 7/-1/-1->6->5 [4] 7/-1/-1->6->5 [5] 7/-1/-1->6->5 [6] 7/14/-1->6->-1 [7] -1/-1/-1->6->5 [8] 7/-1/-1->6->5 [9] 7/-1/-1->6->5 [10] 7/-1/-1->6->5 [11] 7/-1/-1->6->5 [12] 7/-1/-1->6->5 [13] 7/-1/-1->6->5 [14] 7/-1/-1->6->14 [15] -1/-1/-1->6->5 cnode7-008:628129:628991 [6] NCCL INFO P2P Chunksize set to 131072 cnode7-009:270309:271118 [1] NCCL INFO Channel 00/0 : 9[1] -> 10[2] via P2P/CUMEM cnode7-009:270309:271118 [1] NCCL INFO Channel 02/0 : 9[1] -> 10[2] via P2P/CUMEM cnode7-009:270309:271118 [1] NCCL INFO Channel 04/0 : 9[1] -> 10[2] via P2P/CUMEM cnode7-009:270309:271118 [1] NCCL INFO Channel 06/0 : 9[1] -> 10[2] via P2P/CUMEM cnode7-009:270309:271118 [1] NCCL INFO Channel 08/0 : 9[1] -> 10[2] via P2P/CUMEM cnode7-009:270309:271118 [1] NCCL INFO Channel 10/0 : 9[1] -> 10[2] via P2P/CUMEM cnode7-009:270309:271118 [1] NCCL INFO Channel 12/0 : 9[1] -> 10[2] via P2P/CUMEM cnode7-009:270309:271118 [1] NCCL INFO Channel 14/0 : 9[1] -> 10[2] via P2P/CUMEM cnode7-008:628125:628997 [2] NCCL INFO Channel 01/0 : 2[2] -> 3[3] via P2P/CUMEM cnode7-008:628125:628997 [2] NCCL INFO Channel 05/0 : 2[2] -> 3[3] via P2P/CUMEM cnode7-008:628125:628997 [2] NCCL INFO Channel 07/0 : 2[2] -> 3[3] via P2P/CUMEM cnode7-008:628125:628997 [2] NCCL INFO Channel 09/0 : 2[2] -> 3[3] via P2P/CUMEM cnode7-008:628125:628997 [2] NCCL INFO Channel 13/0 : 2[2] -> 3[3] via P2P/CUMEM cnode7-008:628125:628997 [2] NCCL INFO Channel 15/0 : 2[2] -> 3[3] via P2P/CUMEM cnode7-008:628125:628997 [2] NCCL INFO Channel 02/0 : 10[2] -> 2[2] [receive] via NET/IB/2/GDRDMA cnode7-008:628125:628997 [2] NCCL INFO Channel 10/0 : 10[2] -> 2[2] [receive] via NET/IB/2/GDRDMA cnode7-008:628125:628997 [2] NCCL INFO Channel 03/0 : 2[2] -> 10[2] [send] via NET/IB/2/GDRDMA cnode7-008:628125:628997 [2] NCCL INFO Channel 11/0 : 2[2] -> 10[2] [send] via NET/IB/2/GDRDMA cnode7-009:270308:271135 [0] NCCL INFO Channel 02/0 : 8[0] -> 9[1] via P2P/CUMEM cnode7-009:270308:271135 [0] NCCL INFO Channel 04/0 : 8[0] -> 9[1] via P2P/CUMEM cnode7-009:270308:271135 [0] NCCL INFO Channel 06/0 : 8[0] -> 9[1] via P2P/CUMEM cnode7-009:270308:271135 [0] NCCL INFO Channel 10/0 : 8[0] -> 9[1] via P2P/CUMEM cnode7-009:270308:271135 [0] NCCL INFO Channel 12/0 : 8[0] -> 9[1] via P2P/CUMEM cnode7-009:270308:271135 [0] NCCL INFO Channel 14/0 : 8[0] -> 9[1] via P2P/CUMEM cnode7-009:270308:271135 [0] NCCL INFO Channel 01/0 : 8[0] -> 15[7] via P2P/CUMEM cnode7-009:270308:271135 [0] NCCL INFO Channel 03/0 : 8[0] -> 15[7] via P2P/CUMEM cnode7-009:270308:271135 [0] NCCL INFO Channel 05/0 : 8[0] -> 15[7] via P2P/CUMEM cnode7-009:270308:271135 [0] NCCL INFO Channel 07/0 : 8[0] -> 15[7] via P2P/CUMEM cnode7-009:270308:271135 [0] NCCL INFO Channel 09/0 : 8[0] -> 15[7] via P2P/CUMEM cnode7-009:270308:271135 [0] NCCL INFO Channel 11/0 : 8[0] -> 15[7] via P2P/CUMEM cnode7-009:270308:271135 [0] NCCL INFO Channel 13/0 : 8[0] -> 15[7] via P2P/CUMEM cnode7-008:628124:628983 [1] NCCL INFO Channel 01/0 : 1[1] -> 2[2] via P2P/CUMEM cnode7-008:628124:628983 [1] NCCL INFO Channel 03/0 : 1[1] -> 2[2] via P2P/CUMEM cnode7-008:628124:628983 [1] NCCL INFO Channel 05/0 : 1[1] -> 2[2] via P2P/CUMEM cnode7-008:628124:628983 [1] NCCL INFO Channel 07/0 : 1[1] -> 2[2] via P2P/CUMEM cnode7-008:628124:628983 [1] NCCL INFO Channel 09/0 : 1[1] -> 2[2] via P2P/CUMEM cnode7-008:628124:628983 [1] NCCL INFO Channel 11/0 : 1[1] -> 2[2] via P2P/CUMEM cnode7-008:628124:628983 [1] NCCL INFO Channel 13/0 : 1[1] -> 2[2] via P2P/CUMEM cnode7-008:628124:628983 [1] NCCL INFO Channel 15/0 : 1[1] -> 2[2] via P2P/CUMEM cnode7-008:628124:628983 [1] NCCL INFO Channel 01/0 : 9[1] -> 1[1] [receive] via NET/IB/1/GDRDMA cnode7-008:628124:628983 [1] NCCL INFO Channel 09/0 : 9[1] -> 1[1] [receive] via NET/IB/1/GDRDMA cnode7-008:628124:628983 [1] NCCL INFO Channel 00/0 : 1[1] -> 9[1] [send] via NET/IB/1/GDRDMA cnode7-008:628124:628983 [1] NCCL INFO Channel 08/0 : 1[1] -> 9[1] [send] via NET/IB/1/GDRDMA cnode7-008:628123:628980 [0] NCCL INFO Channel 03/0 : 0[0] -> 1[1] via P2P/CUMEM cnode7-008:628123:628980 [0] NCCL INFO Channel 05/0 : 0[0] -> 1[1] via P2P/CUMEM cnode7-008:628123:628980 [0] NCCL INFO Channel 07/0 : 0[0] -> 1[1] via P2P/CUMEM cnode7-008:628123:628980 [0] NCCL INFO Channel 11/0 : 0[0] -> 1[1] via P2P/CUMEM cnode7-008:628123:628980 [0] NCCL INFO Channel 13/0 : 0[0] -> 1[1] via P2P/CUMEM cnode7-008:628123:628980 [0] NCCL INFO Channel 15/0 : 0[0] -> 1[1] via P2P/CUMEM cnode7-008:628123:628980 [0] NCCL INFO Channel 00/0 : 0[0] -> 7[7] via P2P/CUMEM cnode7-008:628123:628980 [0] NCCL INFO Channel 02/0 : 0[0] -> 7[7] via P2P/CUMEM cnode7-008:628123:628980 [0] NCCL INFO Channel 04/0 : 0[0] -> 7[7] via P2P/CUMEM cnode7-008:628123:628980 [0] NCCL INFO Channel 06/0 : 0[0] -> 7[7] via P2P/CUMEM cnode7-008:628123:628980 [0] NCCL INFO Channel 08/0 : 0[0] -> 7[7] via P2P/CUMEM cnode7-008:628123:628980 [0] NCCL INFO Channel 10/0 : 0[0] -> 7[7] via P2P/CUMEM cnode7-008:628123:628980 [0] NCCL INFO Channel 12/0 : 0[0] -> 7[7] via P2P/CUMEM cnode7-008:628123:628980 [0] NCCL INFO Channel 14/0 : 0[0] -> 7[7] via P2P/CUMEM cnode7-009:270310:271224 [2] NCCL INFO Channel 00/0 : 10[2] -> 11[3] via P2P/CUMEM cnode7-009:270310:271224 [2] NCCL INFO Channel 04/0 : 10[2] -> 11[3] via P2P/CUMEM cnode7-009:270310:271224 [2] NCCL INFO Channel 06/0 : 10[2] -> 11[3] via P2P/CUMEM cnode7-009:270310:271224 [2] NCCL INFO Channel 08/0 : 10[2] -> 11[3] via P2P/CUMEM cnode7-009:270310:271224 [2] NCCL INFO Channel 12/0 : 10[2] -> 11[3] via P2P/CUMEM cnode7-009:270310:271224 [2] NCCL INFO Channel 14/0 : 10[2] -> 11[3] via P2P/CUMEM cnode7-009:270310:271224 [2] NCCL INFO Channel 03/0 : 2[2] -> 10[2] [receive] via NET/IB/2/GDRDMA cnode7-009:270310:271224 [2] NCCL INFO Channel 11/0 : 2[2] -> 10[2] [receive] via NET/IB/2/GDRDMA cnode7-009:270310:271224 [2] NCCL INFO Channel 02/0 : 10[2] -> 2[2] [send] via NET/IB/2/GDRDMA cnode7-009:270310:271224 [2] NCCL INFO Channel 10/0 : 10[2] -> 2[2] [send] via NET/IB/2/GDRDMA cnode7-009:270310:271224 [2] NCCL INFO Channel 01/0 : 10[2] -> 9[1] via P2P/CUMEM cnode7-009:270310:271224 [2] NCCL INFO Channel 03/0 : 10[2] -> 9[1] via P2P/CUMEM cnode7-009:270310:271224 [2] NCCL INFO Channel 05/0 : 10[2] -> 9[1] via P2P/CUMEM cnode7-009:270310:271224 [2] NCCL INFO Channel 07/0 : 10[2] -> 9[1] via P2P/CUMEM cnode7-009:270310:271224 [2] NCCL INFO Channel 09/0 : 10[2] -> 9[1] via P2P/CUMEM cnode7-009:270310:271224 [2] NCCL INFO Channel 11/0 : 10[2] -> 9[1] via P2P/CUMEM cnode7-008:628128:628988 [5] NCCL INFO Channel 01/0 : 5[5] -> 6[6] via P2P/CUMEM cnode7-008:628128:628988 [5] NCCL INFO Channel 03/0 : 5[5] -> 6[6] via P2P/CUMEM cnode7-008:628128:628988 [5] NCCL INFO Channel 05/0 : 5[5] -> 6[6] via P2P/CUMEM cnode7-008:628128:628988 [5] NCCL INFO Channel 07/0 : 5[5] -> 6[6] via P2P/CUMEM cnode7-008:628128:628988 [5] NCCL INFO Channel 09/0 : 5[5] -> 6[6] via P2P/CUMEM cnode7-008:628128:628988 [5] NCCL INFO Channel 11/0 : 5[5] -> 6[6] via P2P/CUMEM cnode7-008:628128:628988 [5] NCCL INFO Channel 13/0 : 5[5] -> 6[6] via P2P/CUMEM cnode7-008:628128:628988 [5] NCCL INFO Channel 15/0 : 5[5] -> 6[6] via P2P/CUMEM cnode7-008:628128:628988 [5] NCCL INFO Channel 05/0 : 13[5] -> 5[5] [receive] via NET/IB/6/GDRDMA cnode7-008:628128:628988 [5] NCCL INFO Channel 13/0 : 13[5] -> 5[5] [receive] via NET/IB/6/GDRDMA cnode7-008:628128:628988 [5] NCCL INFO Channel 04/0 : 5[5] -> 13[5] [send] via NET/IB/6/GDRDMA cnode7-008:628128:628988 [5] NCCL INFO Channel 12/0 : 5[5] -> 13[5] [send] via NET/IB/6/GDRDMA cnode7-008:628127:628996 [4] NCCL INFO Channel 01/0 : 4[4] -> 5[5] via P2P/CUMEM cnode7-008:628127:628996 [4] NCCL INFO Channel 03/0 : 4[4] -> 5[5] via P2P/CUMEM cnode7-008:628127:628996 [4] NCCL INFO Channel 07/0 : 4[4] -> 5[5] via P2P/CUMEM cnode7-008:628127:628996 [4] NCCL INFO Channel 09/0 : 4[4] -> 5[5] via P2P/CUMEM cnode7-008:628127:628996 [4] NCCL INFO Channel 11/0 : 4[4] -> 5[5] via P2P/CUMEM cnode7-008:628127:628996 [4] NCCL INFO Channel 15/0 : 4[4] -> 5[5] via P2P/CUMEM cnode7-008:628127:628996 [4] NCCL INFO Channel 04/0 : 12[4] -> 4[4] [receive] via NET/IB/4/GDRDMA cnode7-008:628127:628996 [4] NCCL INFO Channel 12/0 : 12[4] -> 4[4] [receive] via NET/IB/4/GDRDMA cnode7-008:628127:628996 [4] NCCL INFO Channel 05/0 : 4[4] -> 12[4] [send] via NET/IB/4/GDRDMA cnode7-008:628127:628996 [4] NCCL INFO Channel 13/0 : 4[4] -> 12[4] [send] via NET/IB/4/GDRDMA cnode7-008:628126:628984 [3] NCCL INFO Channel 01/0 : 3[3] -> 4[4] via P2P/CUMEM cnode7-008:628126:628984 [3] NCCL INFO Channel 03/0 : 3[3] -> 4[4] via P2P/CUMEM cnode7-008:628126:628984 [3] NCCL INFO Channel 05/0 : 3[3] -> 4[4] via P2P/CUMEM cnode7-008:628126:628984 [3] NCCL INFO Channel 07/0 : 3[3] -> 4[4] via P2P/CUMEM cnode7-008:628126:628984 [3] NCCL INFO Channel 09/0 : 3[3] -> 4[4] via P2P/CUMEM cnode7-008:628126:628984 [3] NCCL INFO Channel 11/0 : 3[3] -> 4[4] via P2P/CUMEM cnode7-008:628126:628984 [3] NCCL INFO Channel 13/0 : 3[3] -> 4[4] via P2P/CUMEM cnode7-008:628126:628984 [3] NCCL INFO Channel 15/0 : 3[3] -> 4[4] via P2P/CUMEM cnode7-008:628126:628984 [3] NCCL INFO Channel 03/0 : 11[3] -> 3[3] [receive] via NET/IB/3/GDRDMA cnode7-008:628126:628984 [3] NCCL INFO Channel 11/0 : 11[3] -> 3[3] [receive] via NET/IB/3/GDRDMA cnode7-008:628126:628984 [3] NCCL INFO Channel 02/0 : 3[3] -> 11[3] [send] via NET/IB/3/GDRDMA cnode7-008:628126:628984 [3] NCCL INFO Channel 10/0 : 3[3] -> 11[3] [send] via NET/IB/3/GDRDMA cnode7-008:628126:628984 [3] NCCL INFO Channel 00/0 : 3[3] -> 2[2] via P2P/CUMEM cnode7-008:628126:628984 [3] NCCL INFO Channel 04/0 : 3[3] -> 2[2] via P2P/CUMEM cnode7-008:628126:628984 [3] NCCL INFO Channel 06/0 : 3[3] -> 2[2] via P2P/CUMEM cnode7-008:628126:628984 [3] NCCL INFO Channel 08/0 : 3[3] -> 2[2] via P2P/CUMEM cnode7-008:628126:628984 [3] NCCL INFO Channel 12/0 : 3[3] -> 2[2] via P2P/CUMEM cnode7-008:628126:628984 [3] NCCL INFO Channel 14/0 : 3[3] -> 2[2] via P2P/CUMEM cnode7-008:628129:628991 [6] NCCL INFO Channel 01/0 : 6[6] -> 7[7] via P2P/CUMEM cnode7-008:628129:628991 [6] NCCL INFO Channel 03/0 : 6[6] -> 7[7] via P2P/CUMEM cnode7-008:628129:628991 [6] NCCL INFO Channel 05/0 : 6[6] -> 7[7] via P2P/CUMEM cnode7-008:628129:628991 [6] NCCL INFO Channel 09/0 : 6[6] -> 7[7] via P2P/CUMEM cnode7-008:628129:628991 [6] NCCL INFO Channel 11/0 : 6[6] -> 7[7] via P2P/CUMEM cnode7-008:628129:628991 [6] NCCL INFO Channel 13/0 : 6[6] -> 7[7] via P2P/CUMEM cnode7-008:628129:628991 [6] NCCL INFO Channel 06/0 : 14[6] -> 6[6] [receive] via NET/IB/7/GDRDMA cnode7-008:628129:628991 [6] NCCL INFO Channel 14/0 : 14[6] -> 6[6] [receive] via NET/IB/7/GDRDMA cnode7-008:628129:628991 [6] NCCL INFO Channel 07/0 : 6[6] -> 14[6] [send] via NET/IB/7/GDRDMA cnode7-008:628129:628991 [6] NCCL INFO Channel 15/0 : 6[6] -> 14[6] [send] via NET/IB/7/GDRDMA cnode7-009:270314:271132 [6] NCCL INFO Channel 00/0 : 14[6] -> 15[7] via P2P/CUMEM cnode7-009:270314:271132 [6] NCCL INFO Channel 02/0 : 14[6] -> 15[7] via P2P/CUMEM cnode7-009:270314:271132 [6] NCCL INFO Channel 04/0 : 14[6] -> 15[7] via P2P/CUMEM cnode7-009:270314:271132 [6] NCCL INFO Channel 08/0 : 14[6] -> 15[7] via P2P/CUMEM cnode7-009:270314:271132 [6] NCCL INFO Channel 10/0 : 14[6] -> 15[7] via P2P/CUMEM cnode7-009:270314:271132 [6] NCCL INFO Channel 12/0 : 14[6] -> 15[7] via P2P/CUMEM cnode7-009:270312:271209 [4] NCCL INFO Channel 00/0 : 12[4] -> 13[5] via P2P/CUMEM cnode7-009:270312:271209 [4] NCCL INFO Channel 02/0 : 12[4] -> 13[5] via P2P/CUMEM cnode7-009:270312:271209 [4] NCCL INFO Channel 06/0 : 12[4] -> 13[5] via P2P/CUMEM cnode7-009:270312:271209 [4] NCCL INFO Channel 08/0 : 12[4] -> 13[5] via P2P/CUMEM cnode7-009:270312:271209 [4] NCCL INFO Channel 10/0 : 12[4] -> 13[5] via P2P/CUMEM cnode7-009:270312:271209 [4] NCCL INFO Channel 14/0 : 12[4] -> 13[5] via P2P/CUMEM cnode7-009:270311:271117 [3] NCCL INFO Channel 02/0 : 3[3] -> 11[3] [receive] via NET/IB/3/GDRDMA cnode7-009:270311:271117 [3] NCCL INFO Channel 10/0 : 3[3] -> 11[3] [receive] via NET/IB/3/GDRDMA cnode7-009:270311:271117 [3] NCCL INFO Channel 03/0 : 11[3] -> 3[3] [send] via NET/IB/3/GDRDMA cnode7-009:270311:271117 [3] NCCL INFO Channel 11/0 : 11[3] -> 3[3] [send] via NET/IB/3/GDRDMA cnode7-009:270311:271117 [3] NCCL INFO Channel 01/0 : 11[3] -> 10[2] via P2P/CUMEM cnode7-009:270311:271117 [3] NCCL INFO Channel 05/0 : 11[3] -> 10[2] via P2P/CUMEM cnode7-009:270311:271117 [3] NCCL INFO Channel 07/0 : 11[3] -> 10[2] via P2P/CUMEM cnode7-009:270311:271117 [3] NCCL INFO Channel 09/0 : 11[3] -> 10[2] via P2P/CUMEM cnode7-009:270311:271117 [3] NCCL INFO Channel 13/0 : 11[3] -> 10[2] via P2P/CUMEM cnode7-009:270311:271117 [3] NCCL INFO Channel 15/0 : 11[3] -> 10[2] via P2P/CUMEM cnode7-009:270309:271118 [1] NCCL INFO Channel 00/0 : 1[1] -> 9[1] [receive] via NET/IB/1/GDRDMA cnode7-009:270309:271118 [1] NCCL INFO Channel 08/0 : 1[1] -> 9[1] [receive] via NET/IB/1/GDRDMA cnode7-009:270309:271118 [1] NCCL INFO Channel 01/0 : 9[1] -> 1[1] [send] via NET/IB/1/GDRDMA cnode7-009:270309:271118 [1] NCCL INFO Channel 09/0 : 9[1] -> 1[1] [send] via NET/IB/1/GDRDMA cnode7-009:270309:271118 [1] NCCL INFO Channel 03/0 : 9[1] -> 8[0] via P2P/CUMEM cnode7-009:270309:271118 [1] NCCL INFO Channel 05/0 : 9[1] -> 8[0] via P2P/CUMEM cnode7-009:270309:271118 [1] NCCL INFO Channel 07/0 : 9[1] -> 8[0] via P2P/CUMEM cnode7-009:270309:271118 [1] NCCL INFO Channel 11/0 : 9[1] -> 8[0] via P2P/CUMEM cnode7-009:270309:271118 [1] NCCL INFO Channel 13/0 : 9[1] -> 8[0] via P2P/CUMEM cnode7-009:270309:271118 [1] NCCL INFO Channel 15/0 : 9[1] -> 8[0] via P2P/CUMEM cnode7-008:628125:628997 [2] NCCL INFO Channel 00/0 : 2[2] -> 1[1] via P2P/CUMEM cnode7-008:628125:628997 [2] NCCL INFO Channel 02/0 : 2[2] -> 1[1] via P2P/CUMEM cnode7-008:628125:628997 [2] NCCL INFO Channel 04/0 : 2[2] -> 1[1] via P2P/CUMEM cnode7-008:628125:628997 [2] NCCL INFO Channel 06/0 : 2[2] -> 1[1] via P2P/CUMEM cnode7-008:628125:628997 [2] NCCL INFO Channel 08/0 : 2[2] -> 1[1] via P2P/CUMEM cnode7-008:628125:628997 [2] NCCL INFO Channel 10/0 : 2[2] -> 1[1] via P2P/CUMEM cnode7-008:628125:628997 [2] NCCL INFO Channel 12/0 : 2[2] -> 1[1] via P2P/CUMEM cnode7-008:628125:628997 [2] NCCL INFO Channel 14/0 : 2[2] -> 1[1] via P2P/CUMEM cnode7-009:270308:271135 [0] NCCL INFO Channel 15/0 : 8[0] -> 15[7] via P2P/CUMEM cnode7-009:270308:271135 [0] NCCL INFO Channel 01/0 : 0[0] -> 8[0] [receive] via NET/IB/0/GDRDMA cnode7-009:270308:271135 [0] NCCL INFO Channel 09/0 : 0[0] -> 8[0] [receive] via NET/IB/0/GDRDMA cnode7-009:270308:271135 [0] NCCL INFO Channel 00/0 : 8[0] -> 0[0] [send] via NET/IB/0/GDRDMA cnode7-009:270308:271135 [0] NCCL INFO Channel 08/0 : 8[0] -> 0[0] [send] via NET/IB/0/GDRDMA cnode7-008:628124:628983 [1] NCCL INFO Channel 02/0 : 1[1] -> 0[0] via P2P/CUMEM cnode7-008:628124:628983 [1] NCCL INFO Channel 04/0 : 1[1] -> 0[0] via P2P/CUMEM cnode7-008:628124:628983 [1] NCCL INFO Channel 06/0 : 1[1] -> 0[0] via P2P/CUMEM cnode7-008:628124:628983 [1] NCCL INFO Channel 10/0 : 1[1] -> 0[0] via P2P/CUMEM cnode7-008:628124:628983 [1] NCCL INFO Channel 12/0 : 1[1] -> 0[0] via P2P/CUMEM cnode7-008:628124:628983 [1] NCCL INFO Channel 14/0 : 1[1] -> 0[0] via P2P/CUMEM cnode7-008:628123:628980 [0] NCCL INFO Channel 00/0 : 8[0] -> 0[0] [receive] via NET/IB/0/GDRDMA cnode7-008:628123:628980 [0] NCCL INFO Channel 08/0 : 8[0] -> 0[0] [receive] via NET/IB/0/GDRDMA cnode7-008:628123:628980 [0] NCCL INFO Channel 01/0 : 0[0] -> 8[0] [send] via NET/IB/0/GDRDMA cnode7-008:628123:628980 [0] NCCL INFO Channel 09/0 : 0[0] -> 8[0] [send] via NET/IB/0/GDRDMA cnode7-009:270310:271224 [2] NCCL INFO Channel 13/0 : 10[2] -> 9[1] via P2P/CUMEM cnode7-009:270310:271224 [2] NCCL INFO Channel 15/0 : 10[2] -> 9[1] via P2P/CUMEM cnode7-008:628130:628985 [7] NCCL INFO Channel 07/0 : 15[7] -> 7[7] [receive] via NET/IB/8/GDRDMA cnode7-008:628130:628985 [7] NCCL INFO Channel 15/0 : 15[7] -> 7[7] [receive] via NET/IB/8/GDRDMA cnode7-008:628130:628985 [7] NCCL INFO Channel 06/0 : 7[7] -> 15[7] [send] via NET/IB/8/GDRDMA cnode7-008:628130:628985 [7] NCCL INFO Channel 14/0 : 7[7] -> 15[7] [send] via NET/IB/8/GDRDMA cnode7-008:628130:628985 [7] NCCL INFO Channel 01/0 : 7[7] -> 0[0] via P2P/CUMEM cnode7-008:628130:628985 [7] NCCL INFO Channel 03/0 : 7[7] -> 0[0] via P2P/CUMEM cnode7-008:628130:628985 [7] NCCL INFO Channel 05/0 : 7[7] -> 0[0] via P2P/CUMEM cnode7-008:628130:628985 [7] NCCL INFO Channel 07/0 : 7[7] -> 0[0] via P2P/CUMEM cnode7-008:628130:628985 [7] NCCL INFO Channel 09/0 : 7[7] -> 0[0] via P2P/CUMEM cnode7-008:628130:628985 [7] NCCL INFO Channel 11/0 : 7[7] -> 0[0] via P2P/CUMEM cnode7-008:628130:628985 [7] NCCL INFO Channel 13/0 : 7[7] -> 0[0] via P2P/CUMEM cnode7-008:628130:628985 [7] NCCL INFO Channel 15/0 : 7[7] -> 0[0] via P2P/CUMEM cnode7-008:628130:628985 [7] NCCL INFO Channel 00/0 : 7[7] -> 6[6] via P2P/CUMEM cnode7-008:628130:628985 [7] NCCL INFO Channel 02/0 : 7[7] -> 6[6] via P2P/CUMEM cnode7-008:628130:628985 [7] NCCL INFO Channel 04/0 : 7[7] -> 6[6] via P2P/CUMEM cnode7-008:628130:628985 [7] NCCL INFO Channel 08/0 : 7[7] -> 6[6] via P2P/CUMEM cnode7-008:628130:628985 [7] NCCL INFO Channel 10/0 : 7[7] -> 6[6] via P2P/CUMEM cnode7-008:628130:628985 [7] NCCL INFO Channel 12/0 : 7[7] -> 6[6] via P2P/CUMEM cnode7-008:628128:628988 [5] NCCL INFO Channel 00/0 : 5[5] -> 4[4] via P2P/CUMEM cnode7-008:628128:628988 [5] NCCL INFO Channel 02/0 : 5[5] -> 4[4] via P2P/CUMEM cnode7-008:628128:628988 [5] NCCL INFO Channel 06/0 : 5[5] -> 4[4] via P2P/CUMEM cnode7-008:628128:628988 [5] NCCL INFO Channel 08/0 : 5[5] -> 4[4] via P2P/CUMEM cnode7-008:628128:628988 [5] NCCL INFO Channel 10/0 : 5[5] -> 4[4] via P2P/CUMEM cnode7-008:628128:628988 [5] NCCL INFO Channel 14/0 : 5[5] -> 4[4] via P2P/CUMEM cnode7-009:270313:271171 [5] NCCL INFO Channel 00/0 : 13[5] -> 14[6] via P2P/CUMEM cnode7-009:270313:271171 [5] NCCL INFO Channel 02/0 : 13[5] -> 14[6] via P2P/CUMEM cnode7-009:270313:271171 [5] NCCL INFO Channel 04/0 : 13[5] -> 14[6] via P2P/CUMEM cnode7-009:270313:271171 [5] NCCL INFO Channel 06/0 : 13[5] -> 14[6] via P2P/CUMEM cnode7-009:270313:271171 [5] NCCL INFO Channel 08/0 : 13[5] -> 14[6] via P2P/CUMEM cnode7-009:270313:271171 [5] NCCL INFO Channel 10/0 : 13[5] -> 14[6] via P2P/CUMEM cnode7-009:270313:271171 [5] NCCL INFO Channel 12/0 : 13[5] -> 14[6] via P2P/CUMEM cnode7-009:270313:271171 [5] NCCL INFO Channel 14/0 : 13[5] -> 14[6] via P2P/CUMEM cnode7-009:270313:271171 [5] NCCL INFO Channel 04/0 : 5[5] -> 13[5] [receive] via NET/IB/6/GDRDMA cnode7-009:270313:271171 [5] NCCL INFO Channel 12/0 : 5[5] -> 13[5] [receive] via NET/IB/6/GDRDMA cnode7-009:270313:271171 [5] NCCL INFO Channel 05/0 : 13[5] -> 5[5] [send] via NET/IB/6/GDRDMA cnode7-009:270313:271171 [5] NCCL INFO Channel 13/0 : 13[5] -> 5[5] [send] via NET/IB/6/GDRDMA cnode7-009:270313:271171 [5] NCCL INFO Channel 01/0 : 13[5] -> 12[4] via P2P/CUMEM cnode7-009:270313:271171 [5] NCCL INFO Channel 03/0 : 13[5] -> 12[4] via P2P/CUMEM cnode7-009:270313:271171 [5] NCCL INFO Channel 07/0 : 13[5] -> 12[4] via P2P/CUMEM cnode7-009:270313:271171 [5] NCCL INFO Channel 09/0 : 13[5] -> 12[4] via P2P/CUMEM cnode7-009:270313:271171 [5] NCCL INFO Channel 11/0 : 13[5] -> 12[4] via P2P/CUMEM cnode7-009:270313:271171 [5] NCCL INFO Channel 15/0 : 13[5] -> 12[4] via P2P/CUMEM cnode7-008:628127:628996 [4] NCCL INFO Channel 00/0 : 4[4] -> 3[3] via P2P/CUMEM cnode7-008:628127:628996 [4] NCCL INFO Channel 02/0 : 4[4] -> 3[3] via P2P/CUMEM cnode7-008:628127:628996 [4] NCCL INFO Channel 04/0 : 4[4] -> 3[3] via P2P/CUMEM cnode7-008:628127:628996 [4] NCCL INFO Channel 06/0 : 4[4] -> 3[3] via P2P/CUMEM cnode7-008:628127:628996 [4] NCCL INFO Channel 08/0 : 4[4] -> 3[3] via P2P/CUMEM cnode7-008:628127:628996 [4] NCCL INFO Channel 10/0 : 4[4] -> 3[3] via P2P/CUMEM cnode7-008:628127:628996 [4] NCCL INFO Channel 12/0 : 4[4] -> 3[3] via P2P/CUMEM cnode7-008:628127:628996 [4] NCCL INFO Channel 14/0 : 4[4] -> 3[3] via P2P/CUMEM cnode7-008:628129:628991 [6] NCCL INFO Channel 00/0 : 6[6] -> 5[5] via P2P/CUMEM cnode7-008:628129:628991 [6] NCCL INFO Channel 02/0 : 6[6] -> 5[5] via P2P/CUMEM cnode7-008:628129:628991 [6] NCCL INFO Channel 04/0 : 6[6] -> 5[5] via P2P/CUMEM cnode7-008:628129:628991 [6] NCCL INFO Channel 06/0 : 6[6] -> 5[5] via P2P/CUMEM cnode7-008:628129:628991 [6] NCCL INFO Channel 08/0 : 6[6] -> 5[5] via P2P/CUMEM cnode7-008:628129:628991 [6] NCCL INFO Channel 10/0 : 6[6] -> 5[5] via P2P/CUMEM cnode7-008:628129:628991 [6] NCCL INFO Channel 12/0 : 6[6] -> 5[5] via P2P/CUMEM cnode7-008:628129:628991 [6] NCCL INFO Channel 14/0 : 6[6] -> 5[5] via P2P/CUMEM cnode7-009:270315:271168 [7] NCCL INFO Channel 06/0 : 7[7] -> 15[7] [receive] via NET/IB/8/GDRDMA cnode7-009:270315:271168 [7] NCCL INFO Channel 14/0 : 7[7] -> 15[7] [receive] via NET/IB/8/GDRDMA cnode7-009:270315:271168 [7] NCCL INFO Channel 07/0 : 15[7] -> 7[7] [send] via NET/IB/8/GDRDMA cnode7-009:270315:271168 [7] NCCL INFO Channel 15/0 : 15[7] -> 7[7] [send] via NET/IB/8/GDRDMA cnode7-009:270315:271168 [7] NCCL INFO Channel 00/0 : 15[7] -> 8[0] via P2P/CUMEM cnode7-009:270315:271168 [7] NCCL INFO Channel 02/0 : 15[7] -> 8[0] via P2P/CUMEM cnode7-009:270315:271168 [7] NCCL INFO Channel 04/0 : 15[7] -> 8[0] via P2P/CUMEM cnode7-009:270315:271168 [7] NCCL INFO Channel 06/0 : 15[7] -> 8[0] via P2P/CUMEM cnode7-009:270315:271168 [7] NCCL INFO Channel 08/0 : 15[7] -> 8[0] via P2P/CUMEM cnode7-009:270315:271168 [7] NCCL INFO Channel 10/0 : 15[7] -> 8[0] via P2P/CUMEM cnode7-009:270315:271168 [7] NCCL INFO Channel 12/0 : 15[7] -> 8[0] via P2P/CUMEM cnode7-009:270315:271168 [7] NCCL INFO Channel 14/0 : 15[7] -> 8[0] via P2P/CUMEM cnode7-009:270315:271168 [7] NCCL INFO Channel 01/0 : 15[7] -> 14[6] via P2P/CUMEM cnode7-009:270315:271168 [7] NCCL INFO Channel 03/0 : 15[7] -> 14[6] via P2P/CUMEM cnode7-009:270315:271168 [7] NCCL INFO Channel 05/0 : 15[7] -> 14[6] via P2P/CUMEM cnode7-009:270315:271168 [7] NCCL INFO Channel 09/0 : 15[7] -> 14[6] via P2P/CUMEM cnode7-009:270315:271168 [7] NCCL INFO Channel 11/0 : 15[7] -> 14[6] via P2P/CUMEM cnode7-009:270315:271168 [7] NCCL INFO Channel 13/0 : 15[7] -> 14[6] via P2P/CUMEM cnode7-009:270314:271132 [6] NCCL INFO Channel 07/0 : 6[6] -> 14[6] [receive] via NET/IB/7/GDRDMA cnode7-009:270314:271132 [6] NCCL INFO Channel 15/0 : 6[6] -> 14[6] [receive] via NET/IB/7/GDRDMA cnode7-009:270314:271132 [6] NCCL INFO Channel 06/0 : 14[6] -> 6[6] [send] via NET/IB/7/GDRDMA cnode7-009:270314:271132 [6] NCCL INFO Channel 14/0 : 14[6] -> 6[6] [send] via NET/IB/7/GDRDMA cnode7-009:270314:271132 [6] NCCL INFO Channel 01/0 : 14[6] -> 13[5] via P2P/CUMEM cnode7-009:270314:271132 [6] NCCL INFO Channel 03/0 : 14[6] -> 13[5] via P2P/CUMEM cnode7-009:270314:271132 [6] NCCL INFO Channel 05/0 : 14[6] -> 13[5] via P2P/CUMEM cnode7-009:270314:271132 [6] NCCL INFO Channel 07/0 : 14[6] -> 13[5] via P2P/CUMEM cnode7-009:270314:271132 [6] NCCL INFO Channel 09/0 : 14[6] -> 13[5] via P2P/CUMEM cnode7-009:270314:271132 [6] NCCL INFO Channel 11/0 : 14[6] -> 13[5] via P2P/CUMEM cnode7-009:270314:271132 [6] NCCL INFO Channel 13/0 : 14[6] -> 13[5] via P2P/CUMEM cnode7-009:270314:271132 [6] NCCL INFO Channel 15/0 : 14[6] -> 13[5] via P2P/CUMEM cnode7-009:270312:271209 [4] NCCL INFO Channel 05/0 : 4[4] -> 12[4] [receive] via NET/IB/4/GDRDMA cnode7-009:270312:271209 [4] NCCL INFO Channel 13/0 : 4[4] -> 12[4] [receive] via NET/IB/4/GDRDMA cnode7-009:270312:271209 [4] NCCL INFO Channel 04/0 : 12[4] -> 4[4] [send] via NET/IB/4/GDRDMA cnode7-009:270312:271209 [4] NCCL INFO Channel 12/0 : 12[4] -> 4[4] [send] via NET/IB/4/GDRDMA cnode7-009:270312:271209 [4] NCCL INFO Channel 01/0 : 12[4] -> 11[3] via P2P/CUMEM cnode7-009:270312:271209 [4] NCCL INFO Channel 03/0 : 12[4] -> 11[3] via P2P/CUMEM cnode7-009:270312:271209 [4] NCCL INFO Channel 05/0 : 12[4] -> 11[3] via P2P/CUMEM cnode7-009:270312:271209 [4] NCCL INFO Channel 07/0 : 12[4] -> 11[3] via P2P/CUMEM cnode7-009:270312:271209 [4] NCCL INFO Channel 09/0 : 12[4] -> 11[3] via P2P/CUMEM cnode7-009:270312:271209 [4] NCCL INFO Channel 11/0 : 12[4] -> 11[3] via P2P/CUMEM cnode7-009:270312:271209 [4] NCCL INFO Channel 13/0 : 12[4] -> 11[3] via P2P/CUMEM cnode7-009:270312:271209 [4] NCCL INFO Channel 15/0 : 12[4] -> 11[3] via P2P/CUMEM cnode7-009:270310:271224 [2] NCCL INFO Connected all rings cnode7-008:628126:628984 [3] NCCL INFO Connected all rings cnode7-008:628126:628984 [3] NCCL INFO Channel 00/0 : 3[3] -> 4[4] via P2P/CUMEM cnode7-008:628126:628984 [3] NCCL INFO Channel 02/0 : 3[3] -> 4[4] via P2P/CUMEM cnode7-008:628126:628984 [3] NCCL INFO Channel 06/0 : 3[3] -> 4[4] via P2P/CUMEM cnode7-008:628126:628984 [3] NCCL INFO Channel 08/0 : 3[3] -> 4[4] via P2P/CUMEM cnode7-008:628126:628984 [3] NCCL INFO Channel 10/0 : 3[3] -> 4[4] via P2P/CUMEM cnode7-008:628126:628984 [3] NCCL INFO Channel 14/0 : 3[3] -> 4[4] via P2P/CUMEM cnode7-009:270311:271117 [3] NCCL INFO Connected all rings cnode7-009:270311:271117 [3] NCCL INFO Channel 01/0 : 11[3] -> 12[4] via P2P/CUMEM cnode7-009:270311:271117 [3] NCCL INFO Channel 03/0 : 11[3] -> 12[4] via P2P/CUMEM cnode7-009:270311:271117 [3] NCCL INFO Channel 05/0 : 11[3] -> 12[4] via P2P/CUMEM cnode7-009:270311:271117 [3] NCCL INFO Channel 07/0 : 11[3] -> 12[4] via P2P/CUMEM cnode7-009:270311:271117 [3] NCCL INFO Channel 09/0 : 11[3] -> 12[4] via P2P/CUMEM cnode7-009:270311:271117 [3] NCCL INFO Channel 11/0 : 11[3] -> 12[4] via P2P/CUMEM cnode7-009:270311:271117 [3] NCCL INFO Channel 13/0 : 11[3] -> 12[4] via P2P/CUMEM cnode7-009:270311:271117 [3] NCCL INFO Channel 15/0 : 11[3] -> 12[4] via P2P/CUMEM cnode7-009:270311:271117 [3] NCCL INFO Channel 03/0 : 3[3] -> 11[3] [receive] via NET/IB/3/GDRDMA cnode7-009:270311:271117 [3] NCCL INFO Channel 11/0 : 3[3] -> 11[3] [receive] via NET/IB/3/GDRDMA cnode7-009:270309:271118 [1] NCCL INFO Connected all rings cnode7-009:270309:271118 [1] NCCL INFO Channel 01/0 : 9[1] -> 10[2] via P2P/CUMEM cnode7-009:270309:271118 [1] NCCL INFO Channel 03/0 : 9[1] -> 10[2] via P2P/CUMEM cnode7-009:270309:271118 [1] NCCL INFO Channel 05/0 : 9[1] -> 10[2] via P2P/CUMEM cnode7-009:270309:271118 [1] NCCL INFO Channel 07/0 : 9[1] -> 10[2] via P2P/CUMEM cnode7-009:270309:271118 [1] NCCL INFO Channel 09/0 : 9[1] -> 10[2] via P2P/CUMEM cnode7-009:270309:271118 [1] NCCL INFO Channel 11/0 : 9[1] -> 10[2] via P2P/CUMEM cnode7-009:270309:271118 [1] NCCL INFO Channel 13/0 : 9[1] -> 10[2] via P2P/CUMEM cnode7-009:270309:271118 [1] NCCL INFO Channel 15/0 : 9[1] -> 10[2] via P2P/CUMEM cnode7-009:270309:271118 [1] NCCL INFO Channel 01/0 : 1[1] -> 9[1] [receive] via NET/IB/1/GDRDMA cnode7-009:270309:271118 [1] NCCL INFO Channel 09/0 : 1[1] -> 9[1] [receive] via NET/IB/1/GDRDMA cnode7-009:270309:271118 [1] NCCL INFO Channel 00/0 : 9[1] -> 8[0] via P2P/CUMEM cnode7-009:270309:271118 [1] NCCL INFO Channel 02/0 : 9[1] -> 8[0] via P2P/CUMEM cnode7-009:270309:271118 [1] NCCL INFO Channel 04/0 : 9[1] -> 8[0] via P2P/CUMEM cnode7-009:270309:271118 [1] NCCL INFO Channel 06/0 : 9[1] -> 8[0] via P2P/CUMEM cnode7-009:270309:271118 [1] NCCL INFO Channel 08/0 : 9[1] -> 8[0] via P2P/CUMEM cnode7-009:270309:271118 [1] NCCL INFO Channel 10/0 : 9[1] -> 8[0] via P2P/CUMEM cnode7-009:270309:271118 [1] NCCL INFO Channel 12/0 : 9[1] -> 8[0] via P2P/CUMEM cnode7-009:270309:271118 [1] NCCL INFO Channel 14/0 : 9[1] -> 8[0] via P2P/CUMEM cnode7-008:628125:628997 [2] NCCL INFO Connected all rings cnode7-008:628125:628997 [2] NCCL INFO Channel 00/0 : 2[2] -> 3[3] via P2P/CUMEM cnode7-008:628125:628997 [2] NCCL INFO Channel 02/0 : 2[2] -> 3[3] via P2P/CUMEM cnode7-008:628125:628997 [2] NCCL INFO Channel 04/0 : 2[2] -> 3[3] via P2P/CUMEM cnode7-008:628125:628997 [2] NCCL INFO Channel 06/0 : 2[2] -> 3[3] via P2P/CUMEM cnode7-008:628125:628997 [2] NCCL INFO Channel 08/0 : 2[2] -> 3[3] via P2P/CUMEM cnode7-008:628125:628997 [2] NCCL INFO Channel 10/0 : 2[2] -> 3[3] via P2P/CUMEM cnode7-008:628125:628997 [2] NCCL INFO Channel 12/0 : 2[2] -> 3[3] via P2P/CUMEM cnode7-008:628125:628997 [2] NCCL INFO Channel 14/0 : 2[2] -> 3[3] via P2P/CUMEM cnode7-008:628125:628997 [2] NCCL INFO Channel 02/0 : 2[2] -> 10[2] [send] via NET/IB/2/GDRDMA cnode7-008:628125:628997 [2] NCCL INFO Channel 10/0 : 2[2] -> 10[2] [send] via NET/IB/2/GDRDMA cnode7-008:628125:628997 [2] NCCL INFO Channel 01/0 : 2[2] -> 1[1] via P2P/CUMEM cnode7-008:628125:628997 [2] NCCL INFO Channel 03/0 : 2[2] -> 1[1] via P2P/CUMEM cnode7-008:628125:628997 [2] NCCL INFO Channel 05/0 : 2[2] -> 1[1] via P2P/CUMEM cnode7-008:628125:628997 [2] NCCL INFO Channel 07/0 : 2[2] -> 1[1] via P2P/CUMEM cnode7-008:628125:628997 [2] NCCL INFO Channel 09/0 : 2[2] -> 1[1] via P2P/CUMEM cnode7-008:628125:628997 [2] NCCL INFO Channel 11/0 : 2[2] -> 1[1] via P2P/CUMEM cnode7-008:628125:628997 [2] NCCL INFO Channel 13/0 : 2[2] -> 1[1] via P2P/CUMEM cnode7-008:628125:628997 [2] NCCL INFO Channel 15/0 : 2[2] -> 1[1] via P2P/CUMEM cnode7-009:270308:271135 [0] NCCL INFO Connected all rings cnode7-009:270308:271135 [0] NCCL INFO Channel 00/0 : 8[0] -> 9[1] via P2P/CUMEM cnode7-009:270308:271135 [0] NCCL INFO Channel 03/0 : 8[0] -> 9[1] via P2P/CUMEM cnode7-009:270308:271135 [0] NCCL INFO Channel 05/0 : 8[0] -> 9[1] via P2P/CUMEM cnode7-009:270308:271135 [0] NCCL INFO Channel 07/0 : 8[0] -> 9[1] via P2P/CUMEM cnode7-009:270308:271135 [0] NCCL INFO Channel 08/0 : 8[0] -> 9[1] via P2P/CUMEM cnode7-009:270308:271135 [0] NCCL INFO Channel 11/0 : 8[0] -> 9[1] via P2P/CUMEM cnode7-009:270308:271135 [0] NCCL INFO Channel 13/0 : 8[0] -> 9[1] via P2P/CUMEM cnode7-009:270308:271135 [0] NCCL INFO Channel 15/0 : 8[0] -> 9[1] via P2P/CUMEM cnode7-009:270308:271135 [0] NCCL INFO Channel 02/0 : 8[0] -> 15[7] via P2P/CUMEM cnode7-009:270308:271135 [0] NCCL INFO Channel 04/0 : 8[0] -> 15[7] via P2P/CUMEM cnode7-009:270308:271135 [0] NCCL INFO Channel 06/0 : 8[0] -> 15[7] via P2P/CUMEM cnode7-009:270308:271135 [0] NCCL INFO Channel 10/0 : 8[0] -> 15[7] via P2P/CUMEM cnode7-009:270308:271135 [0] NCCL INFO Channel 12/0 : 8[0] -> 15[7] via P2P/CUMEM cnode7-009:270308:271135 [0] NCCL INFO Channel 14/0 : 8[0] -> 15[7] via P2P/CUMEM cnode7-009:270308:271135 [0] NCCL INFO Channel 00/0 : 0[0] -> 8[0] [receive] via NET/IB/0/GDRDMA cnode7-009:270308:271135 [0] NCCL INFO Channel 08/0 : 0[0] -> 8[0] [receive] via NET/IB/0/GDRDMA cnode7-008:628124:628983 [1] NCCL INFO Connected all rings cnode7-008:628124:628983 [1] NCCL INFO Channel 00/0 : 1[1] -> 2[2] via P2P/CUMEM cnode7-008:628124:628983 [1] NCCL INFO Channel 04/0 : 1[1] -> 2[2] via P2P/CUMEM cnode7-008:628124:628983 [1] NCCL INFO Channel 06/0 : 1[1] -> 2[2] via P2P/CUMEM cnode7-008:628124:628983 [1] NCCL INFO Channel 08/0 : 1[1] -> 2[2] via P2P/CUMEM cnode7-008:628124:628983 [1] NCCL INFO Channel 12/0 : 1[1] -> 2[2] via P2P/CUMEM cnode7-008:628124:628983 [1] NCCL INFO Channel 14/0 : 1[1] -> 2[2] via P2P/CUMEM cnode7-008:628124:628983 [1] NCCL INFO Channel 01/0 : 1[1] -> 9[1] [send] via NET/IB/1/GDRDMA cnode7-008:628124:628983 [1] NCCL INFO Channel 09/0 : 1[1] -> 9[1] [send] via NET/IB/1/GDRDMA cnode7-008:628124:628983 [1] NCCL INFO Channel 00/0 : 1[1] -> 0[0] via P2P/CUMEM cnode7-008:628124:628983 [1] NCCL INFO Channel 03/0 : 1[1] -> 0[0] via P2P/CUMEM cnode7-008:628124:628983 [1] NCCL INFO Channel 05/0 : 1[1] -> 0[0] via P2P/CUMEM cnode7-008:628124:628983 [1] NCCL INFO Channel 07/0 : 1[1] -> 0[0] via P2P/CUMEM cnode7-008:628124:628983 [1] NCCL INFO Channel 08/0 : 1[1] -> 0[0] via P2P/CUMEM cnode7-008:628124:628983 [1] NCCL INFO Channel 11/0 : 1[1] -> 0[0] via P2P/CUMEM cnode7-008:628124:628983 [1] NCCL INFO Channel 13/0 : 1[1] -> 0[0] via P2P/CUMEM cnode7-008:628124:628983 [1] NCCL INFO Channel 15/0 : 1[1] -> 0[0] via P2P/CUMEM cnode7-008:628123:628980 [0] NCCL INFO Connected all rings cnode7-008:628123:628980 [0] NCCL INFO Channel 00/0 : 0[0] -> 1[1] via P2P/CUMEM cnode7-008:628123:628980 [0] NCCL INFO Channel 02/0 : 0[0] -> 1[1] via P2P/CUMEM cnode7-008:628123:628980 [0] NCCL INFO Channel 04/0 : 0[0] -> 1[1] via P2P/CUMEM cnode7-008:628123:628980 [0] NCCL INFO Channel 06/0 : 0[0] -> 1[1] via P2P/CUMEM cnode7-008:628123:628980 [0] NCCL INFO Channel 08/0 : 0[0] -> 1[1] via P2P/CUMEM cnode7-008:628123:628980 [0] NCCL INFO Channel 10/0 : 0[0] -> 1[1] via P2P/CUMEM cnode7-008:628123:628980 [0] NCCL INFO Channel 12/0 : 0[0] -> 1[1] via P2P/CUMEM cnode7-008:628123:628980 [0] NCCL INFO Channel 14/0 : 0[0] -> 1[1] via P2P/CUMEM cnode7-008:628123:628980 [0] NCCL INFO Channel 01/0 : 0[0] -> 7[7] via P2P/CUMEM cnode7-008:628123:628980 [0] NCCL INFO Channel 03/0 : 0[0] -> 7[7] via P2P/CUMEM cnode7-008:628123:628980 [0] NCCL INFO Channel 05/0 : 0[0] -> 7[7] via P2P/CUMEM cnode7-008:628123:628980 [0] NCCL INFO Channel 07/0 : 0[0] -> 7[7] via P2P/CUMEM cnode7-008:628123:628980 [0] NCCL INFO Channel 09/0 : 0[0] -> 7[7] via P2P/CUMEM cnode7-008:628123:628980 [0] NCCL INFO Channel 11/0 : 0[0] -> 7[7] via P2P/CUMEM cnode7-008:628123:628980 [0] NCCL INFO Channel 13/0 : 0[0] -> 7[7] via P2P/CUMEM cnode7-008:628123:628980 [0] NCCL INFO Channel 15/0 : 0[0] -> 7[7] via P2P/CUMEM cnode7-008:628123:628980 [0] NCCL INFO Channel 00/0 : 0[0] -> 8[0] [send] via NET/IB/0/GDRDMA cnode7-008:628123:628980 [0] NCCL INFO Channel 08/0 : 0[0] -> 8[0] [send] via NET/IB/0/GDRDMA cnode7-009:270310:271224 [2] NCCL INFO Channel 01/0 : 10[2] -> 11[3] via P2P/CUMEM cnode7-009:270310:271224 [2] NCCL INFO Channel 02/0 : 10[2] -> 11[3] via P2P/CUMEM cnode7-009:270310:271224 [2] NCCL INFO Channel 05/0 : 10[2] -> 11[3] via P2P/CUMEM cnode7-009:270310:271224 [2] NCCL INFO Channel 07/0 : 10[2] -> 11[3] via P2P/CUMEM cnode7-009:270310:271224 [2] NCCL INFO Channel 09/0 : 10[2] -> 11[3] via P2P/CUMEM cnode7-009:270310:271224 [2] NCCL INFO Channel 10/0 : 10[2] -> 11[3] via P2P/CUMEM cnode7-009:270310:271224 [2] NCCL INFO Channel 13/0 : 10[2] -> 11[3] via P2P/CUMEM cnode7-009:270310:271224 [2] NCCL INFO Channel 15/0 : 10[2] -> 11[3] via P2P/CUMEM cnode7-009:270310:271224 [2] NCCL INFO Channel 02/0 : 2[2] -> 10[2] [receive] via NET/IB/2/GDRDMA cnode7-009:270310:271224 [2] NCCL INFO Channel 10/0 : 2[2] -> 10[2] [receive] via NET/IB/2/GDRDMA cnode7-009:270310:271224 [2] NCCL INFO Channel 00/0 : 10[2] -> 9[1] via P2P/CUMEM cnode7-009:270310:271224 [2] NCCL INFO Channel 04/0 : 10[2] -> 9[1] via P2P/CUMEM cnode7-009:270310:271224 [2] NCCL INFO Channel 06/0 : 10[2] -> 9[1] via P2P/CUMEM cnode7-009:270310:271224 [2] NCCL INFO Channel 08/0 : 10[2] -> 9[1] via P2P/CUMEM cnode7-009:270310:271224 [2] NCCL INFO Channel 12/0 : 10[2] -> 9[1] via P2P/CUMEM cnode7-009:270310:271224 [2] NCCL INFO Channel 14/0 : 10[2] -> 9[1] via P2P/CUMEM cnode7-008:628130:628985 [7] NCCL INFO Connected all rings cnode7-008:628130:628985 [7] NCCL INFO Channel 07/0 : 7[7] -> 15[7] [send] via NET/IB/8/GDRDMA cnode7-008:628130:628985 [7] NCCL INFO Channel 15/0 : 7[7] -> 15[7] [send] via NET/IB/8/GDRDMA cnode7-008:628130:628985 [7] NCCL INFO Channel 02/0 : 7[7] -> 0[0] via P2P/CUMEM cnode7-008:628130:628985 [7] NCCL INFO Channel 04/0 : 7[7] -> 0[0] via P2P/CUMEM cnode7-008:628130:628985 [7] NCCL INFO Channel 06/0 : 7[7] -> 0[0] via P2P/CUMEM cnode7-008:628130:628985 [7] NCCL INFO Channel 10/0 : 7[7] -> 0[0] via P2P/CUMEM cnode7-008:628130:628985 [7] NCCL INFO Channel 12/0 : 7[7] -> 0[0] via P2P/CUMEM cnode7-008:628130:628985 [7] NCCL INFO Channel 14/0 : 7[7] -> 0[0] via P2P/CUMEM cnode7-008:628130:628985 [7] NCCL INFO Channel 01/0 : 7[7] -> 6[6] via P2P/CUMEM cnode7-008:628130:628985 [7] NCCL INFO Channel 03/0 : 7[7] -> 6[6] via P2P/CUMEM cnode7-008:628130:628985 [7] NCCL INFO Channel 05/0 : 7[7] -> 6[6] via P2P/CUMEM cnode7-008:628130:628985 [7] NCCL INFO Channel 06/0 : 7[7] -> 6[6] via P2P/CUMEM cnode7-008:628130:628985 [7] NCCL INFO Channel 09/0 : 7[7] -> 6[6] via P2P/CUMEM cnode7-008:628130:628985 [7] NCCL INFO Channel 11/0 : 7[7] -> 6[6] via P2P/CUMEM cnode7-008:628130:628985 [7] NCCL INFO Channel 13/0 : 7[7] -> 6[6] via P2P/CUMEM cnode7-008:628130:628985 [7] NCCL INFO Channel 14/0 : 7[7] -> 6[6] via P2P/CUMEM cnode7-008:628128:628988 [5] NCCL INFO Connected all rings cnode7-008:628128:628988 [5] NCCL INFO Channel 00/0 : 5[5] -> 6[6] via P2P/CUMEM cnode7-008:628128:628988 [5] NCCL INFO Channel 02/0 : 5[5] -> 6[6] via P2P/CUMEM cnode7-008:628128:628988 [5] NCCL INFO Channel 04/0 : 5[5] -> 6[6] via P2P/CUMEM cnode7-008:628128:628988 [5] NCCL INFO Channel 08/0 : 5[5] -> 6[6] via P2P/CUMEM cnode7-008:628128:628988 [5] NCCL INFO Channel 10/0 : 5[5] -> 6[6] via P2P/CUMEM cnode7-008:628128:628988 [5] NCCL INFO Channel 12/0 : 5[5] -> 6[6] via P2P/CUMEM cnode7-008:628128:628988 [5] NCCL INFO Channel 05/0 : 5[5] -> 13[5] [send] via NET/IB/6/GDRDMA cnode7-008:628128:628988 [5] NCCL INFO Channel 13/0 : 5[5] -> 13[5] [send] via NET/IB/6/GDRDMA cnode7-008:628128:628988 [5] NCCL INFO Channel 01/0 : 5[5] -> 4[4] via P2P/CUMEM cnode7-008:628128:628988 [5] NCCL INFO Channel 03/0 : 5[5] -> 4[4] via P2P/CUMEM cnode7-008:628128:628988 [5] NCCL INFO Channel 04/0 : 5[5] -> 4[4] via P2P/CUMEM cnode7-008:628128:628988 [5] NCCL INFO Channel 07/0 : 5[5] -> 4[4] via P2P/CUMEM cnode7-008:628128:628988 [5] NCCL INFO Channel 09/0 : 5[5] -> 4[4] via P2P/CUMEM cnode7-008:628128:628988 [5] NCCL INFO Channel 11/0 : 5[5] -> 4[4] via P2P/CUMEM cnode7-008:628128:628988 [5] NCCL INFO Channel 12/0 : 5[5] -> 4[4] via P2P/CUMEM cnode7-008:628128:628988 [5] NCCL INFO Channel 15/0 : 5[5] -> 4[4] via P2P/CUMEM cnode7-009:270313:271171 [5] NCCL INFO Connected all rings cnode7-009:270313:271171 [5] NCCL INFO Channel 01/0 : 13[5] -> 14[6] via P2P/CUMEM cnode7-009:270313:271171 [5] NCCL INFO Channel 03/0 : 13[5] -> 14[6] via P2P/CUMEM cnode7-009:270313:271171 [5] NCCL INFO Channel 05/0 : 13[5] -> 14[6] via P2P/CUMEM cnode7-009:270313:271171 [5] NCCL INFO Channel 07/0 : 13[5] -> 14[6] via P2P/CUMEM cnode7-009:270313:271171 [5] NCCL INFO Channel 09/0 : 13[5] -> 14[6] via P2P/CUMEM cnode7-009:270313:271171 [5] NCCL INFO Channel 11/0 : 13[5] -> 14[6] via P2P/CUMEM cnode7-009:270313:271171 [5] NCCL INFO Channel 13/0 : 13[5] -> 14[6] via P2P/CUMEM cnode7-009:270313:271171 [5] NCCL INFO Channel 15/0 : 13[5] -> 14[6] via P2P/CUMEM cnode7-009:270313:271171 [5] NCCL INFO Channel 05/0 : 5[5] -> 13[5] [receive] via NET/IB/6/GDRDMA cnode7-009:270313:271171 [5] NCCL INFO Channel 13/0 : 5[5] -> 13[5] [receive] via NET/IB/6/GDRDMA cnode7-009:270313:271171 [5] NCCL INFO Channel 00/0 : 13[5] -> 12[4] via P2P/CUMEM cnode7-009:270313:271171 [5] NCCL INFO Channel 02/0 : 13[5] -> 12[4] via P2P/CUMEM cnode7-009:270313:271171 [5] NCCL INFO Channel 04/0 : 13[5] -> 12[4] via P2P/CUMEM cnode7-009:270313:271171 [5] NCCL INFO Channel 06/0 : 13[5] -> 12[4] via P2P/CUMEM cnode7-009:270313:271171 [5] NCCL INFO Channel 08/0 : 13[5] -> 12[4] via P2P/CUMEM cnode7-009:270313:271171 [5] NCCL INFO Channel 10/0 : 13[5] -> 12[4] via P2P/CUMEM cnode7-009:270313:271171 [5] NCCL INFO Channel 12/0 : 13[5] -> 12[4] via P2P/CUMEM cnode7-009:270313:271171 [5] NCCL INFO Channel 14/0 : 13[5] -> 12[4] via P2P/CUMEM cnode7-008:628127:628996 [4] NCCL INFO Connected all rings cnode7-008:628127:628996 [4] NCCL INFO Channel 00/0 : 4[4] -> 5[5] via P2P/CUMEM cnode7-008:628127:628996 [4] NCCL INFO Channel 02/0 : 4[4] -> 5[5] via P2P/CUMEM cnode7-008:628127:628996 [4] NCCL INFO Channel 04/0 : 4[4] -> 5[5] via P2P/CUMEM cnode7-008:628127:628996 [4] NCCL INFO Channel 06/0 : 4[4] -> 5[5] via P2P/CUMEM cnode7-008:628127:628996 [4] NCCL INFO Channel 08/0 : 4[4] -> 5[5] via P2P/CUMEM cnode7-008:628127:628996 [4] NCCL INFO Channel 10/0 : 4[4] -> 5[5] via P2P/CUMEM cnode7-008:628127:628996 [4] NCCL INFO Channel 12/0 : 4[4] -> 5[5] via P2P/CUMEM cnode7-008:628127:628996 [4] NCCL INFO Channel 14/0 : 4[4] -> 5[5] via P2P/CUMEM cnode7-008:628127:628996 [4] NCCL INFO Channel 04/0 : 4[4] -> 12[4] [send] via NET/IB/4/GDRDMA cnode7-008:628127:628996 [4] NCCL INFO Channel 12/0 : 4[4] -> 12[4] [send] via NET/IB/4/GDRDMA cnode7-008:628127:628996 [4] NCCL INFO Channel 01/0 : 4[4] -> 3[3] via P2P/CUMEM cnode7-008:628127:628996 [4] NCCL INFO Channel 03/0 : 4[4] -> 3[3] via P2P/CUMEM cnode7-008:628127:628996 [4] NCCL INFO Channel 05/0 : 4[4] -> 3[3] via P2P/CUMEM cnode7-008:628127:628996 [4] NCCL INFO Channel 07/0 : 4[4] -> 3[3] via P2P/CUMEM cnode7-008:628127:628996 [4] NCCL INFO Channel 09/0 : 4[4] -> 3[3] via P2P/CUMEM cnode7-008:628127:628996 [4] NCCL INFO Channel 11/0 : 4[4] -> 3[3] via P2P/CUMEM cnode7-008:628127:628996 [4] NCCL INFO Channel 13/0 : 4[4] -> 3[3] via P2P/CUMEM cnode7-008:628127:628996 [4] NCCL INFO Channel 15/0 : 4[4] -> 3[3] via P2P/CUMEM cnode7-008:628126:628984 [3] NCCL INFO Channel 03/0 : 3[3] -> 11[3] [send] via NET/IB/3/GDRDMA cnode7-008:628126:628984 [3] NCCL INFO Channel 11/0 : 3[3] -> 11[3] [send] via NET/IB/3/GDRDMA cnode7-008:628126:628984 [3] NCCL INFO Channel 01/0 : 3[3] -> 2[2] via P2P/CUMEM cnode7-008:628126:628984 [3] NCCL INFO Channel 02/0 : 3[3] -> 2[2] via P2P/CUMEM cnode7-008:628126:628984 [3] NCCL INFO Channel 05/0 : 3[3] -> 2[2] via P2P/CUMEM cnode7-008:628126:628984 [3] NCCL INFO Channel 07/0 : 3[3] -> 2[2] via P2P/CUMEM cnode7-008:628126:628984 [3] NCCL INFO Channel 09/0 : 3[3] -> 2[2] via P2P/CUMEM cnode7-008:628126:628984 [3] NCCL INFO Channel 10/0 : 3[3] -> 2[2] via P2P/CUMEM cnode7-008:628126:628984 [3] NCCL INFO Channel 13/0 : 3[3] -> 2[2] via P2P/CUMEM cnode7-008:628126:628984 [3] NCCL INFO Channel 15/0 : 3[3] -> 2[2] via P2P/CUMEM cnode7-008:628129:628991 [6] NCCL INFO Connected all rings cnode7-008:628129:628991 [6] NCCL INFO Channel 00/0 : 6[6] -> 7[7] via P2P/CUMEM cnode7-008:628129:628991 [6] NCCL INFO Channel 02/0 : 6[6] -> 7[7] via P2P/CUMEM cnode7-008:628129:628991 [6] NCCL INFO Channel 04/0 : 6[6] -> 7[7] via P2P/CUMEM cnode7-008:628129:628991 [6] NCCL INFO Channel 06/0 : 6[6] -> 7[7] via P2P/CUMEM cnode7-008:628129:628991 [6] NCCL INFO Channel 08/0 : 6[6] -> 7[7] via P2P/CUMEM cnode7-008:628129:628991 [6] NCCL INFO Channel 10/0 : 6[6] -> 7[7] via P2P/CUMEM cnode7-008:628129:628991 [6] NCCL INFO Channel 12/0 : 6[6] -> 7[7] via P2P/CUMEM cnode7-008:628129:628991 [6] NCCL INFO Channel 14/0 : 6[6] -> 7[7] via P2P/CUMEM cnode7-008:628129:628991 [6] NCCL INFO Channel 06/0 : 6[6] -> 14[6] [send] via NET/IB/7/GDRDMA cnode7-008:628129:628991 [6] NCCL INFO Channel 14/0 : 6[6] -> 14[6] [send] via NET/IB/7/GDRDMA cnode7-008:628129:628991 [6] NCCL INFO Channel 01/0 : 6[6] -> 5[5] via P2P/CUMEM cnode7-008:628129:628991 [6] NCCL INFO Channel 03/0 : 6[6] -> 5[5] via P2P/CUMEM cnode7-008:628129:628991 [6] NCCL INFO Channel 05/0 : 6[6] -> 5[5] via P2P/CUMEM cnode7-008:628129:628991 [6] NCCL INFO Channel 07/0 : 6[6] -> 5[5] via P2P/CUMEM cnode7-008:628129:628991 [6] NCCL INFO Channel 09/0 : 6[6] -> 5[5] via P2P/CUMEM cnode7-008:628129:628991 [6] NCCL INFO Channel 11/0 : 6[6] -> 5[5] via P2P/CUMEM cnode7-008:628129:628991 [6] NCCL INFO Channel 13/0 : 6[6] -> 5[5] via P2P/CUMEM cnode7-008:628129:628991 [6] NCCL INFO Channel 15/0 : 6[6] -> 5[5] via P2P/CUMEM cnode7-009:270314:271132 [6] NCCL INFO Connected all rings cnode7-009:270314:271132 [6] NCCL INFO Channel 01/0 : 14[6] -> 15[7] via P2P/CUMEM cnode7-009:270314:271132 [6] NCCL INFO Channel 03/0 : 14[6] -> 15[7] via P2P/CUMEM cnode7-009:270314:271132 [6] NCCL INFO Channel 05/0 : 14[6] -> 15[7] via P2P/CUMEM cnode7-009:270314:271132 [6] NCCL INFO Channel 06/0 : 14[6] -> 15[7] via P2P/CUMEM cnode7-009:270314:271132 [6] NCCL INFO Channel 09/0 : 14[6] -> 15[7] via P2P/CUMEM cnode7-009:270314:271132 [6] NCCL INFO Channel 11/0 : 14[6] -> 15[7] via P2P/CUMEM cnode7-009:270314:271132 [6] NCCL INFO Channel 13/0 : 14[6] -> 15[7] via P2P/CUMEM cnode7-009:270314:271132 [6] NCCL INFO Channel 14/0 : 14[6] -> 15[7] via P2P/CUMEM cnode7-009:270314:271132 [6] NCCL INFO Channel 06/0 : 6[6] -> 14[6] [receive] via NET/IB/7/GDRDMA cnode7-009:270314:271132 [6] NCCL INFO Channel 14/0 : 6[6] -> 14[6] [receive] via NET/IB/7/GDRDMA cnode7-009:270314:271132 [6] NCCL INFO Channel 00/0 : 14[6] -> 13[5] via P2P/CUMEM cnode7-009:270314:271132 [6] NCCL INFO Channel 02/0 : 14[6] -> 13[5] via P2P/CUMEM cnode7-009:270314:271132 [6] NCCL INFO Channel 04/0 : 14[6] -> 13[5] via P2P/CUMEM cnode7-009:270314:271132 [6] NCCL INFO Channel 08/0 : 14[6] -> 13[5] via P2P/CUMEM cnode7-009:270314:271132 [6] NCCL INFO Channel 10/0 : 14[6] -> 13[5] via P2P/CUMEM cnode7-009:270314:271132 [6] NCCL INFO Channel 12/0 : 14[6] -> 13[5] via P2P/CUMEM cnode7-009:270315:271168 [7] NCCL INFO Connected all rings cnode7-009:270315:271168 [7] NCCL INFO Channel 07/0 : 7[7] -> 15[7] [receive] via NET/IB/8/GDRDMA cnode7-009:270315:271168 [7] NCCL INFO Channel 15/0 : 7[7] -> 15[7] [receive] via NET/IB/8/GDRDMA cnode7-009:270315:271168 [7] NCCL INFO Channel 01/0 : 15[7] -> 8[0] via P2P/CUMEM cnode7-009:270315:271168 [7] NCCL INFO Channel 03/0 : 15[7] -> 8[0] via P2P/CUMEM cnode7-009:270315:271168 [7] NCCL INFO Channel 05/0 : 15[7] -> 8[0] via P2P/CUMEM cnode7-009:270315:271168 [7] NCCL INFO Channel 07/0 : 15[7] -> 8[0] via P2P/CUMEM cnode7-009:270315:271168 [7] NCCL INFO Channel 09/0 : 15[7] -> 8[0] via P2P/CUMEM cnode7-009:270315:271168 [7] NCCL INFO Channel 11/0 : 15[7] -> 8[0] via P2P/CUMEM cnode7-009:270315:271168 [7] NCCL INFO Channel 13/0 : 15[7] -> 8[0] via P2P/CUMEM cnode7-009:270315:271168 [7] NCCL INFO Channel 15/0 : 15[7] -> 8[0] via P2P/CUMEM cnode7-009:270315:271168 [7] NCCL INFO Channel 00/0 : 15[7] -> 14[6] via P2P/CUMEM cnode7-009:270315:271168 [7] NCCL INFO Channel 02/0 : 15[7] -> 14[6] via P2P/CUMEM cnode7-009:270315:271168 [7] NCCL INFO Channel 04/0 : 15[7] -> 14[6] via P2P/CUMEM cnode7-009:270315:271168 [7] NCCL INFO Channel 06/0 : 15[7] -> 14[6] via P2P/CUMEM cnode7-009:270315:271168 [7] NCCL INFO Channel 08/0 : 15[7] -> 14[6] via P2P/CUMEM cnode7-009:270315:271168 [7] NCCL INFO Channel 10/0 : 15[7] -> 14[6] via P2P/CUMEM cnode7-009:270315:271168 [7] NCCL INFO Channel 12/0 : 15[7] -> 14[6] via P2P/CUMEM cnode7-009:270315:271168 [7] NCCL INFO Channel 14/0 : 15[7] -> 14[6] via P2P/CUMEM cnode7-009:270312:271209 [4] NCCL INFO Connected all rings cnode7-009:270312:271209 [4] NCCL INFO Channel 01/0 : 12[4] -> 13[5] via P2P/CUMEM cnode7-009:270312:271209 [4] NCCL INFO Channel 03/0 : 12[4] -> 13[5] via P2P/CUMEM cnode7-009:270312:271209 [4] NCCL INFO Channel 04/0 : 12[4] -> 13[5] via P2P/CUMEM cnode7-009:270312:271209 [4] NCCL INFO Channel 07/0 : 12[4] -> 13[5] via P2P/CUMEM cnode7-009:270312:271209 [4] NCCL INFO Channel 09/0 : 12[4] -> 13[5] via P2P/CUMEM cnode7-009:270312:271209 [4] NCCL INFO Channel 11/0 : 12[4] -> 13[5] via P2P/CUMEM cnode7-009:270312:271209 [4] NCCL INFO Channel 12/0 : 12[4] -> 13[5] via P2P/CUMEM cnode7-009:270312:271209 [4] NCCL INFO Channel 15/0 : 12[4] -> 13[5] via P2P/CUMEM cnode7-009:270312:271209 [4] NCCL INFO Channel 04/0 : 4[4] -> 12[4] [receive] via NET/IB/4/GDRDMA cnode7-009:270312:271209 [4] NCCL INFO Channel 12/0 : 4[4] -> 12[4] [receive] via NET/IB/4/GDRDMA cnode7-009:270312:271209 [4] NCCL INFO Channel 00/0 : 12[4] -> 11[3] via P2P/CUMEM cnode7-009:270312:271209 [4] NCCL INFO Channel 02/0 : 12[4] -> 11[3] via P2P/CUMEM cnode7-009:270312:271209 [4] NCCL INFO Channel 06/0 : 12[4] -> 11[3] via P2P/CUMEM cnode7-009:270312:271209 [4] NCCL INFO Channel 08/0 : 12[4] -> 11[3] via P2P/CUMEM cnode7-009:270312:271209 [4] NCCL INFO Channel 10/0 : 12[4] -> 11[3] via P2P/CUMEM cnode7-009:270312:271209 [4] NCCL INFO Channel 14/0 : 12[4] -> 11[3] via P2P/CUMEM cnode7-009:270311:271117 [3] NCCL INFO Channel 00/0 : 11[3] -> 10[2] via P2P/CUMEM cnode7-009:270311:271117 [3] NCCL INFO Channel 02/0 : 11[3] -> 10[2] via P2P/CUMEM cnode7-009:270311:271117 [3] NCCL INFO Channel 04/0 : 11[3] -> 10[2] via P2P/CUMEM cnode7-009:270311:271117 [3] NCCL INFO Channel 06/0 : 11[3] -> 10[2] via P2P/CUMEM cnode7-009:270311:271117 [3] NCCL INFO Channel 08/0 : 11[3] -> 10[2] via P2P/CUMEM cnode7-009:270311:271117 [3] NCCL INFO Channel 10/0 : 11[3] -> 10[2] via P2P/CUMEM cnode7-009:270311:271117 [3] NCCL INFO Channel 12/0 : 11[3] -> 10[2] via P2P/CUMEM cnode7-009:270311:271117 [3] NCCL INFO Channel 14/0 : 11[3] -> 10[2] via P2P/CUMEM cnode7-009:270309:271118 [1] NCCL INFO Connected all trees cnode7-009:270315:271168 [7] NCCL INFO Connected all trees cnode7-009:270314:271132 [6] NCCL INFO Connected all trees cnode7-009:270313:271171 [5] NCCL INFO Connected all trees cnode7-009:270308:271135 [0] NCCL INFO Connected all trees cnode7-008:628130:628985 [7] NCCL INFO Connected all trees cnode7-008:628124:628983 [1] NCCL INFO Connected all trees cnode7-008:628123:628980 [0] NCCL INFO Connected all trees cnode7-008:628127:628996 [4] NCCL INFO Connected all trees cnode7-008:628129:628991 [6] NCCL INFO Connected all trees cnode7-008:628128:628988 [5] NCCL INFO Connected all trees cnode7-008:628126:628984 [3] NCCL INFO Connected all trees cnode7-008:628125:628997 [2] NCCL INFO Connected all trees cnode7-009:270311:271117 [3] NCCL INFO Connected all trees cnode7-009:270310:271224 [2] NCCL INFO Connected all trees cnode7-009:270312:271209 [4] NCCL INFO Connected all trees cnode7-009:270308:271135 [0] NCCL INFO NVLS comm 0x555563d3b5b0 headRank 0 nHeads 8 buffSize 4194304 memSize 2097152 nvlsPerRankSize 201326592 nvlsTotalSize 1610612736 cnode7-008:628124:628983 [1] NCCL INFO NVLS comm 0x55557c01e980 headRank 1 nHeads 8 buffSize 4194304 memSize 2097152 nvlsPerRankSize 201326592 nvlsTotalSize 1610612736 cnode7-008:628123:628980 [0] NCCL INFO NVLS comm 0x5555647681e0 headRank 0 nHeads 8 buffSize 4194304 memSize 2097152 nvlsPerRankSize 201326592 nvlsTotalSize 1610612736 cnode7-009:270310:271224 [2] NCCL INFO NVLS comm 0x555560a14700 headRank 2 nHeads 8 buffSize 4194304 memSize 2097152 nvlsPerRankSize 201326592 nvlsTotalSize 1610612736 cnode7-008:628130:628985 [7] NCCL INFO NVLS comm 0x55556ca1b270 headRank 7 nHeads 8 buffSize 4194304 memSize 2097152 nvlsPerRankSize 201326592 nvlsTotalSize 1610612736 cnode7-008:628128:628988 [5] NCCL INFO NVLS comm 0x555575c23df0 headRank 5 nHeads 8 buffSize 4194304 memSize 2097152 nvlsPerRankSize 201326592 nvlsTotalSize 1610612736 cnode7-009:270313:271171 [5] NCCL INFO NVLS comm 0x555560c1ad60 headRank 5 nHeads 8 buffSize 4194304 memSize 2097152 nvlsPerRankSize 201326592 nvlsTotalSize 1610612736 cnode7-008:628127:628996 [4] NCCL INFO NVLS comm 0x55558101ada0 headRank 4 nHeads 8 buffSize 4194304 memSize 2097152 nvlsPerRankSize 201326592 nvlsTotalSize 1610612736 cnode7-008:628126:628984 [3] NCCL INFO NVLS comm 0x555566a1a9d0 headRank 3 nHeads 8 buffSize 4194304 memSize 2097152 nvlsPerRankSize 201326592 nvlsTotalSize 1610612736 cnode7-008:628129:628991 [6] NCCL INFO NVLS comm 0x55557501a8c0 headRank 6 nHeads 8 buffSize 4194304 memSize 2097152 nvlsPerRankSize 201326592 nvlsTotalSize 1610612736 cnode7-009:270314:271132 [6] NCCL INFO NVLS comm 0x55557bc1ae80 headRank 6 nHeads 8 buffSize 4194304 memSize 2097152 nvlsPerRankSize 201326592 nvlsTotalSize 1610612736 cnode7-009:270315:271168 [7] NCCL INFO NVLS comm 0x555561a1aca0 headRank 7 nHeads 8 buffSize 4194304 memSize 2097152 nvlsPerRankSize 201326592 nvlsTotalSize 1610612736 cnode7-009:270312:271209 [4] NCCL INFO NVLS comm 0x55557261ed20 headRank 4 nHeads 8 buffSize 4194304 memSize 2097152 nvlsPerRankSize 201326592 nvlsTotalSize 1610612736 cnode7-009:270311:271117 [3] NCCL INFO NVLS comm 0x555569a227f0 headRank 3 nHeads 8 buffSize 4194304 memSize 2097152 nvlsPerRankSize 201326592 nvlsTotalSize 1610612736 cnode7-009:270309:271118 [1] NCCL INFO NVLS comm 0x55558161ad80 headRank 1 nHeads 8 buffSize 4194304 memSize 2097152 nvlsPerRankSize 201326592 nvlsTotalSize 1610612736 cnode7-008:628125:628997 [2] NCCL INFO NVLS comm 0x55557c41cde0 headRank 2 nHeads 8 buffSize 4194304 memSize 2097152 nvlsPerRankSize 201326592 nvlsTotalSize 1610612736 cnode7-009:270308:271135 [0] NCCL INFO Channel 02/0 : 0[0] -> 8[0] [receive] via NET/IB/0/GDRDMA cnode7-009:270308:271135 [0] NCCL INFO Channel 03/0 : 0[0] -> 8[0] [receive] via NET/IB/0/GDRDMA cnode7-009:270308:271135 [0] NCCL INFO Channel 04/0 : 0[0] -> 8[0] [receive] via NET/IB/0/GDRDMA cnode7-009:270308:271135 [0] NCCL INFO Channel 05/0 : 0[0] -> 8[0] [receive] via NET/IB/0/GDRDMA cnode7-009:270308:271135 [0] NCCL INFO Channel 06/0 : 0[0] -> 8[0] [receive] via NET/IB/0/GDRDMA cnode7-009:270308:271135 [0] NCCL INFO Channel 07/0 : 0[0] -> 8[0] [receive] via NET/IB/0/GDRDMA cnode7-009:270308:271135 [0] NCCL INFO Channel 10/0 : 0[0] -> 8[0] [receive] via NET/IB/0/GDRDMA cnode7-009:270308:271135 [0] NCCL INFO Channel 11/0 : 0[0] -> 8[0] [receive] via NET/IB/0/GDRDMA cnode7-008:628124:628983 [1] NCCL INFO Channel 00/0 : 9[1] -> 1[1] [receive] via NET/IB/1/GDRDMA cnode7-008:628124:628983 [1] NCCL INFO Channel 02/0 : 9[1] -> 1[1] [receive] via NET/IB/1/GDRDMA cnode7-008:628124:628983 [1] NCCL INFO Channel 03/0 : 9[1] -> 1[1] [receive] via NET/IB/1/GDRDMA cnode7-008:628124:628983 [1] NCCL INFO Channel 04/0 : 9[1] -> 1[1] [receive] via NET/IB/1/GDRDMA cnode7-008:628124:628983 [1] NCCL INFO Channel 05/0 : 9[1] -> 1[1] [receive] via NET/IB/1/GDRDMA cnode7-008:628124:628983 [1] NCCL INFO Channel 06/0 : 9[1] -> 1[1] [receive] via NET/IB/1/GDRDMA cnode7-008:628124:628983 [1] NCCL INFO Channel 07/0 : 9[1] -> 1[1] [receive] via NET/IB/1/GDRDMA cnode7-008:628124:628983 [1] NCCL INFO Channel 08/0 : 9[1] -> 1[1] [receive] via NET/IB/1/GDRDMA cnode7-008:628123:628980 [0] NCCL INFO Channel 01/0 : 8[0] -> 0[0] [receive] via NET/IB/0/GDRDMA cnode7-008:628123:628980 [0] NCCL INFO Channel 02/0 : 8[0] -> 0[0] [receive] via NET/IB/0/GDRDMA cnode7-008:628123:628980 [0] NCCL INFO Channel 03/0 : 8[0] -> 0[0] [receive] via NET/IB/0/GDRDMA cnode7-008:628123:628980 [0] NCCL INFO Channel 04/0 : 8[0] -> 0[0] [receive] via NET/IB/0/GDRDMA cnode7-008:628123:628980 [0] NCCL INFO Channel 05/0 : 8[0] -> 0[0] [receive] via NET/IB/0/GDRDMA cnode7-008:628123:628980 [0] NCCL INFO Channel 06/0 : 8[0] -> 0[0] [receive] via NET/IB/0/GDRDMA cnode7-008:628123:628980 [0] NCCL INFO Channel 07/0 : 8[0] -> 0[0] [receive] via NET/IB/0/GDRDMA cnode7-008:628123:628980 [0] NCCL INFO Channel 09/0 : 8[0] -> 0[0] [receive] via NET/IB/0/GDRDMA cnode7-009:270310:271224 [2] NCCL INFO Channel 00/0 : 2[2] -> 10[2] [receive] via NET/IB/2/GDRDMA cnode7-009:270310:271224 [2] NCCL INFO Channel 01/0 : 2[2] -> 10[2] [receive] via NET/IB/2/GDRDMA cnode7-009:270310:271224 [2] NCCL INFO Channel 04/0 : 2[2] -> 10[2] [receive] via NET/IB/2/GDRDMA cnode7-009:270310:271224 [2] NCCL INFO Channel 05/0 : 2[2] -> 10[2] [receive] via NET/IB/2/GDRDMA cnode7-009:270310:271224 [2] NCCL INFO Channel 06/0 : 2[2] -> 10[2] [receive] via NET/IB/2/GDRDMA cnode7-009:270310:271224 [2] NCCL INFO Channel 07/0 : 2[2] -> 10[2] [receive] via NET/IB/2/GDRDMA cnode7-009:270310:271224 [2] NCCL INFO Channel 08/0 : 2[2] -> 10[2] [receive] via NET/IB/2/GDRDMA cnode7-009:270310:271224 [2] NCCL INFO Channel 09/0 : 2[2] -> 10[2] [receive] via NET/IB/2/GDRDMA cnode7-008:628130:628985 [7] NCCL INFO Channel 00/0 : 15[7] -> 7[7] [receive] via NET/IB/8/GDRDMA cnode7-008:628130:628985 [7] NCCL INFO Channel 01/0 : 15[7] -> 7[7] [receive] via NET/IB/8/GDRDMA cnode7-008:628130:628985 [7] NCCL INFO Channel 02/0 : 15[7] -> 7[7] [receive] via NET/IB/8/GDRDMA cnode7-008:628130:628985 [7] NCCL INFO Channel 03/0 : 15[7] -> 7[7] [receive] via NET/IB/8/GDRDMA cnode7-008:628130:628985 [7] NCCL INFO Channel 04/0 : 15[7] -> 7[7] [receive] via NET/IB/8/GDRDMA cnode7-008:628130:628985 [7] NCCL INFO Channel 05/0 : 15[7] -> 7[7] [receive] via NET/IB/8/GDRDMA cnode7-008:628130:628985 [7] NCCL INFO Channel 06/0 : 15[7] -> 7[7] [receive] via NET/IB/8/GDRDMA cnode7-008:628130:628985 [7] NCCL INFO Channel 08/0 : 15[7] -> 7[7] [receive] via NET/IB/8/GDRDMA cnode7-008:628128:628988 [5] NCCL INFO Channel 00/0 : 13[5] -> 5[5] [receive] via NET/IB/6/GDRDMA cnode7-008:628128:628988 [5] NCCL INFO Channel 01/0 : 13[5] -> 5[5] [receive] via NET/IB/6/GDRDMA cnode7-008:628128:628988 [5] NCCL INFO Channel 02/0 : 13[5] -> 5[5] [receive] via NET/IB/6/GDRDMA cnode7-008:628128:628988 [5] NCCL INFO Channel 03/0 : 13[5] -> 5[5] [receive] via NET/IB/6/GDRDMA cnode7-008:628128:628988 [5] NCCL INFO Channel 04/0 : 13[5] -> 5[5] [receive] via NET/IB/6/GDRDMA cnode7-008:628128:628988 [5] NCCL INFO Channel 06/0 : 13[5] -> 5[5] [receive] via NET/IB/6/GDRDMA cnode7-008:628128:628988 [5] NCCL INFO Channel 07/0 : 13[5] -> 5[5] [receive] via NET/IB/6/GDRDMA cnode7-008:628128:628988 [5] NCCL INFO Channel 08/0 : 13[5] -> 5[5] [receive] via NET/IB/6/GDRDMA cnode7-009:270313:271171 [5] NCCL INFO Channel 00/0 : 5[5] -> 13[5] [receive] via NET/IB/6/GDRDMA cnode7-009:270313:271171 [5] NCCL INFO Channel 01/0 : 5[5] -> 13[5] [receive] via NET/IB/6/GDRDMA cnode7-009:270313:271171 [5] NCCL INFO Channel 02/0 : 5[5] -> 13[5] [receive] via NET/IB/6/GDRDMA cnode7-009:270313:271171 [5] NCCL INFO Channel 03/0 : 5[5] -> 13[5] [receive] via NET/IB/6/GDRDMA cnode7-009:270313:271171 [5] NCCL INFO Channel 06/0 : 5[5] -> 13[5] [receive] via NET/IB/6/GDRDMA cnode7-009:270313:271171 [5] NCCL INFO Channel 07/0 : 5[5] -> 13[5] [receive] via NET/IB/6/GDRDMA cnode7-009:270313:271171 [5] NCCL INFO Channel 08/0 : 5[5] -> 13[5] [receive] via NET/IB/6/GDRDMA cnode7-009:270313:271171 [5] NCCL INFO Channel 09/0 : 5[5] -> 13[5] [receive] via NET/IB/6/GDRDMA cnode7-008:628127:628996 [4] NCCL INFO Channel 00/0 : 12[4] -> 4[4] [receive] via NET/IB/4/GDRDMA cnode7-008:628127:628996 [4] NCCL INFO Channel 01/0 : 12[4] -> 4[4] [receive] via NET/IB/4/GDRDMA cnode7-008:628127:628996 [4] NCCL INFO Channel 02/0 : 12[4] -> 4[4] [receive] via NET/IB/4/GDRDMA cnode7-008:628127:628996 [4] NCCL INFO Channel 03/0 : 12[4] -> 4[4] [receive] via NET/IB/4/GDRDMA cnode7-008:628127:628996 [4] NCCL INFO Channel 05/0 : 12[4] -> 4[4] [receive] via NET/IB/4/GDRDMA cnode7-008:628127:628996 [4] NCCL INFO Channel 06/0 : 12[4] -> 4[4] [receive] via NET/IB/4/GDRDMA cnode7-008:628127:628996 [4] NCCL INFO Channel 07/0 : 12[4] -> 4[4] [receive] via NET/IB/4/GDRDMA cnode7-008:628127:628996 [4] NCCL INFO Channel 08/0 : 12[4] -> 4[4] [receive] via NET/IB/4/GDRDMA cnode7-008:628126:628984 [3] NCCL INFO Channel 00/0 : 11[3] -> 3[3] [receive] via NET/IB/3/GDRDMA cnode7-008:628126:628984 [3] NCCL INFO Channel 01/0 : 11[3] -> 3[3] [receive] via NET/IB/3/GDRDMA cnode7-008:628126:628984 [3] NCCL INFO Channel 02/0 : 11[3] -> 3[3] [receive] via NET/IB/3/GDRDMA cnode7-008:628126:628984 [3] NCCL INFO Channel 04/0 : 11[3] -> 3[3] [receive] via NET/IB/3/GDRDMA cnode7-008:628126:628984 [3] NCCL INFO Channel 05/0 : 11[3] -> 3[3] [receive] via NET/IB/3/GDRDMA cnode7-008:628126:628984 [3] NCCL INFO Channel 06/0 : 11[3] -> 3[3] [receive] via NET/IB/3/GDRDMA cnode7-008:628126:628984 [3] NCCL INFO Channel 07/0 : 11[3] -> 3[3] [receive] via NET/IB/3/GDRDMA cnode7-008:628126:628984 [3] NCCL INFO Channel 08/0 : 11[3] -> 3[3] [receive] via NET/IB/3/GDRDMA cnode7-008:628129:628991 [6] NCCL INFO Channel 00/0 : 14[6] -> 6[6] [receive] via NET/IB/7/GDRDMA cnode7-008:628129:628991 [6] NCCL INFO Channel 01/0 : 14[6] -> 6[6] [receive] via NET/IB/7/GDRDMA cnode7-008:628129:628991 [6] NCCL INFO Channel 02/0 : 14[6] -> 6[6] [receive] via NET/IB/7/GDRDMA cnode7-008:628129:628991 [6] NCCL INFO Channel 03/0 : 14[6] -> 6[6] [receive] via NET/IB/7/GDRDMA cnode7-008:628129:628991 [6] NCCL INFO Channel 04/0 : 14[6] -> 6[6] [receive] via NET/IB/7/GDRDMA cnode7-008:628129:628991 [6] NCCL INFO Channel 05/0 : 14[6] -> 6[6] [receive] via NET/IB/7/GDRDMA cnode7-008:628129:628991 [6] NCCL INFO Channel 07/0 : 14[6] -> 6[6] [receive] via NET/IB/7/GDRDMA cnode7-008:628129:628991 [6] NCCL INFO Channel 08/0 : 14[6] -> 6[6] [receive] via NET/IB/7/GDRDMA cnode7-009:270315:271168 [7] NCCL INFO Channel 00/0 : 7[7] -> 15[7] [receive] via NET/IB/8/GDRDMA cnode7-009:270315:271168 [7] NCCL INFO Channel 01/0 : 7[7] -> 15[7] [receive] via NET/IB/8/GDRDMA cnode7-009:270315:271168 [7] NCCL INFO Channel 02/0 : 7[7] -> 15[7] [receive] via NET/IB/8/GDRDMA cnode7-009:270315:271168 [7] NCCL INFO Channel 03/0 : 7[7] -> 15[7] [receive] via NET/IB/8/GDRDMA cnode7-009:270315:271168 [7] NCCL INFO Channel 04/0 : 7[7] -> 15[7] [receive] via NET/IB/8/GDRDMA cnode7-009:270315:271168 [7] NCCL INFO Channel 05/0 : 7[7] -> 15[7] [receive] via NET/IB/8/GDRDMA cnode7-009:270315:271168 [7] NCCL INFO Channel 08/0 : 7[7] -> 15[7] [receive] via NET/IB/8/GDRDMA cnode7-009:270315:271168 [7] NCCL INFO Channel 09/0 : 7[7] -> 15[7] [receive] via NET/IB/8/GDRDMA cnode7-009:270314:271132 [6] NCCL INFO Channel 00/0 : 6[6] -> 14[6] [receive] via NET/IB/7/GDRDMA cnode7-009:270314:271132 [6] NCCL INFO Channel 01/0 : 6[6] -> 14[6] [receive] via NET/IB/7/GDRDMA cnode7-009:270314:271132 [6] NCCL INFO Channel 02/0 : 6[6] -> 14[6] [receive] via NET/IB/7/GDRDMA cnode7-009:270314:271132 [6] NCCL INFO Channel 03/0 : 6[6] -> 14[6] [receive] via NET/IB/7/GDRDMA cnode7-009:270314:271132 [6] NCCL INFO Channel 04/0 : 6[6] -> 14[6] [receive] via NET/IB/7/GDRDMA cnode7-009:270314:271132 [6] NCCL INFO Channel 05/0 : 6[6] -> 14[6] [receive] via NET/IB/7/GDRDMA cnode7-009:270314:271132 [6] NCCL INFO Channel 08/0 : 6[6] -> 14[6] [receive] via NET/IB/7/GDRDMA cnode7-009:270314:271132 [6] NCCL INFO Channel 09/0 : 6[6] -> 14[6] [receive] via NET/IB/7/GDRDMA cnode7-009:270312:271209 [4] NCCL INFO Channel 00/0 : 4[4] -> 12[4] [receive] via NET/IB/4/GDRDMA cnode7-009:270312:271209 [4] NCCL INFO Channel 01/0 : 4[4] -> 12[4] [receive] via NET/IB/4/GDRDMA cnode7-009:270312:271209 [4] NCCL INFO Channel 02/0 : 4[4] -> 12[4] [receive] via NET/IB/4/GDRDMA cnode7-009:270312:271209 [4] NCCL INFO Channel 03/0 : 4[4] -> 12[4] [receive] via NET/IB/4/GDRDMA cnode7-009:270312:271209 [4] NCCL INFO Channel 06/0 : 4[4] -> 12[4] [receive] via NET/IB/4/GDRDMA cnode7-009:270312:271209 [4] NCCL INFO Channel 07/0 : 4[4] -> 12[4] [receive] via NET/IB/4/GDRDMA cnode7-009:270312:271209 [4] NCCL INFO Channel 08/0 : 4[4] -> 12[4] [receive] via NET/IB/4/GDRDMA cnode7-009:270312:271209 [4] NCCL INFO Channel 09/0 : 4[4] -> 12[4] [receive] via NET/IB/4/GDRDMA cnode7-009:270311:271117 [3] NCCL INFO Channel 00/0 : 3[3] -> 11[3] [receive] via NET/IB/3/GDRDMA cnode7-009:270311:271117 [3] NCCL INFO Channel 01/0 : 3[3] -> 11[3] [receive] via NET/IB/3/GDRDMA cnode7-009:270311:271117 [3] NCCL INFO Channel 04/0 : 3[3] -> 11[3] [receive] via NET/IB/3/GDRDMA cnode7-009:270311:271117 [3] NCCL INFO Channel 05/0 : 3[3] -> 11[3] [receive] via NET/IB/3/GDRDMA cnode7-009:270311:271117 [3] NCCL INFO Channel 06/0 : 3[3] -> 11[3] [receive] via NET/IB/3/GDRDMA cnode7-009:270311:271117 [3] NCCL INFO Channel 07/0 : 3[3] -> 11[3] [receive] via NET/IB/3/GDRDMA cnode7-009:270311:271117 [3] NCCL INFO Channel 08/0 : 3[3] -> 11[3] [receive] via NET/IB/3/GDRDMA cnode7-009:270311:271117 [3] NCCL INFO Channel 09/0 : 3[3] -> 11[3] [receive] via NET/IB/3/GDRDMA cnode7-009:270309:271118 [1] NCCL INFO Channel 02/0 : 1[1] -> 9[1] [receive] via NET/IB/1/GDRDMA cnode7-009:270309:271118 [1] NCCL INFO Channel 03/0 : 1[1] -> 9[1] [receive] via NET/IB/1/GDRDMA cnode7-009:270309:271118 [1] NCCL INFO Channel 04/0 : 1[1] -> 9[1] [receive] via NET/IB/1/GDRDMA cnode7-009:270309:271118 [1] NCCL INFO Channel 05/0 : 1[1] -> 9[1] [receive] via NET/IB/1/GDRDMA cnode7-009:270309:271118 [1] NCCL INFO Channel 06/0 : 1[1] -> 9[1] [receive] via NET/IB/1/GDRDMA cnode7-009:270309:271118 [1] NCCL INFO Channel 07/0 : 1[1] -> 9[1] [receive] via NET/IB/1/GDRDMA cnode7-009:270309:271118 [1] NCCL INFO Channel 10/0 : 1[1] -> 9[1] [receive] via NET/IB/1/GDRDMA cnode7-009:270309:271118 [1] NCCL INFO Channel 11/0 : 1[1] -> 9[1] [receive] via NET/IB/1/GDRDMA cnode7-008:628125:628997 [2] NCCL INFO Channel 00/0 : 10[2] -> 2[2] [receive] via NET/IB/2/GDRDMA cnode7-008:628125:628997 [2] NCCL INFO Channel 01/0 : 10[2] -> 2[2] [receive] via NET/IB/2/GDRDMA cnode7-008:628125:628997 [2] NCCL INFO Channel 03/0 : 10[2] -> 2[2] [receive] via NET/IB/2/GDRDMA cnode7-008:628125:628997 [2] NCCL INFO Channel 04/0 : 10[2] -> 2[2] [receive] via NET/IB/2/GDRDMA cnode7-008:628125:628997 [2] NCCL INFO Channel 05/0 : 10[2] -> 2[2] [receive] via NET/IB/2/GDRDMA cnode7-008:628125:628997 [2] NCCL INFO Channel 06/0 : 10[2] -> 2[2] [receive] via NET/IB/2/GDRDMA cnode7-008:628125:628997 [2] NCCL INFO Channel 07/0 : 10[2] -> 2[2] [receive] via NET/IB/2/GDRDMA cnode7-008:628125:628997 [2] NCCL INFO Channel 08/0 : 10[2] -> 2[2] [receive] via NET/IB/2/GDRDMA cnode7-009:270308:271135 [0] NCCL INFO Channel 12/0 : 0[0] -> 8[0] [receive] via NET/IB/0/GDRDMA cnode7-009:270308:271135 [0] NCCL INFO Channel 13/0 : 0[0] -> 8[0] [receive] via NET/IB/0/GDRDMA cnode7-009:270308:271135 [0] NCCL INFO Channel 14/0 : 0[0] -> 8[0] [receive] via NET/IB/0/GDRDMA cnode7-009:270308:271135 [0] NCCL INFO Channel 15/0 : 0[0] -> 8[0] [receive] via NET/IB/0/GDRDMA cnode7-009:270308:271135 [0] NCCL INFO Channel 01/0 : 8[0] -> 0[0] [send] via NET/IB/0/GDRDMA cnode7-009:270308:271135 [0] NCCL INFO Channel 02/0 : 8[0] -> 0[0] [send] via NET/IB/0/GDRDMA cnode7-009:270308:271135 [0] NCCL INFO Channel 03/0 : 8[0] -> 0[0] [send] via NET/IB/0/GDRDMA cnode7-009:270308:271135 [0] NCCL INFO Channel 04/0 : 8[0] -> 0[0] [send] via NET/IB/0/GDRDMA cnode7-009:270308:271135 [0] NCCL INFO Channel 05/0 : 8[0] -> 0[0] [send] via NET/IB/0/GDRDMA cnode7-009:270308:271135 [0] NCCL INFO Channel 06/0 : 8[0] -> 0[0] [send] via NET/IB/0/GDRDMA cnode7-009:270308:271135 [0] NCCL INFO Channel 07/0 : 8[0] -> 0[0] [send] via NET/IB/0/GDRDMA cnode7-009:270308:271135 [0] NCCL INFO Channel 09/0 : 8[0] -> 0[0] [send] via NET/IB/0/GDRDMA cnode7-009:270308:271135 [0] NCCL INFO Channel 10/0 : 8[0] -> 0[0] [send] via NET/IB/0/GDRDMA cnode7-009:270308:271135 [0] NCCL INFO Channel 11/0 : 8[0] -> 0[0] [send] via NET/IB/0/GDRDMA cnode7-009:270308:271135 [0] NCCL INFO Channel 12/0 : 8[0] -> 0[0] [send] via NET/IB/0/GDRDMA cnode7-009:270308:271135 [0] NCCL INFO Channel 13/0 : 8[0] -> 0[0] [send] via NET/IB/0/GDRDMA cnode7-009:270308:271135 [0] NCCL INFO Channel 14/0 : 8[0] -> 0[0] [send] via NET/IB/0/GDRDMA cnode7-009:270308:271135 [0] NCCL INFO Channel 15/0 : 8[0] -> 0[0] [send] via NET/IB/0/GDRDMA cnode7-008:628128:628988 [5] NCCL INFO Channel 09/0 : 13[5] -> 5[5] [receive] via NET/IB/6/GDRDMA cnode7-008:628128:628988 [5] NCCL INFO Channel 10/0 : 13[5] -> 5[5] [receive] via NET/IB/6/GDRDMA cnode7-008:628128:628988 [5] NCCL INFO Channel 11/0 : 13[5] -> 5[5] [receive] via NET/IB/6/GDRDMA cnode7-008:628128:628988 [5] NCCL INFO Channel 12/0 : 13[5] -> 5[5] [receive] via NET/IB/6/GDRDMA cnode7-008:628128:628988 [5] NCCL INFO Channel 14/0 : 13[5] -> 5[5] [receive] via NET/IB/6/GDRDMA cnode7-008:628128:628988 [5] NCCL INFO Channel 15/0 : 13[5] -> 5[5] [receive] via NET/IB/6/GDRDMA cnode7-008:628128:628988 [5] NCCL INFO Channel 00/0 : 5[5] -> 13[5] [send] via NET/IB/6/GDRDMA cnode7-008:628128:628988 [5] NCCL INFO Channel 01/0 : 5[5] -> 13[5] [send] via NET/IB/6/GDRDMA cnode7-008:628128:628988 [5] NCCL INFO Channel 02/0 : 5[5] -> 13[5] [send] via NET/IB/6/GDRDMA cnode7-008:628128:628988 [5] NCCL INFO Channel 03/0 : 5[5] -> 13[5] [send] via NET/IB/6/GDRDMA cnode7-008:628128:628988 [5] NCCL INFO Channel 06/0 : 5[5] -> 13[5] [send] via NET/IB/6/GDRDMA cnode7-008:628128:628988 [5] NCCL INFO Channel 07/0 : 5[5] -> 13[5] [send] via NET/IB/6/GDRDMA cnode7-008:628128:628988 [5] NCCL INFO Channel 08/0 : 5[5] -> 13[5] [send] via NET/IB/6/GDRDMA cnode7-008:628128:628988 [5] NCCL INFO Channel 09/0 : 5[5] -> 13[5] [send] via NET/IB/6/GDRDMA cnode7-008:628128:628988 [5] NCCL INFO Channel 10/0 : 5[5] -> 13[5] [send] via NET/IB/6/GDRDMA cnode7-008:628128:628988 [5] NCCL INFO Channel 11/0 : 5[5] -> 13[5] [send] via NET/IB/6/GDRDMA cnode7-008:628128:628988 [5] NCCL INFO Channel 14/0 : 5[5] -> 13[5] [send] via NET/IB/6/GDRDMA cnode7-008:628128:628988 [5] NCCL INFO Channel 15/0 : 5[5] -> 13[5] [send] via NET/IB/6/GDRDMA cnode7-009:270313:271171 [5] NCCL INFO Channel 10/0 : 5[5] -> 13[5] [receive] via NET/IB/6/GDRDMA cnode7-009:270313:271171 [5] NCCL INFO Channel 11/0 : 5[5] -> 13[5] [receive] via NET/IB/6/GDRDMA cnode7-009:270313:271171 [5] NCCL INFO Channel 14/0 : 5[5] -> 13[5] [receive] via NET/IB/6/GDRDMA cnode7-009:270313:271171 [5] NCCL INFO Channel 15/0 : 5[5] -> 13[5] [receive] via NET/IB/6/GDRDMA cnode7-009:270313:271171 [5] NCCL INFO Channel 00/0 : 13[5] -> 5[5] [send] via NET/IB/6/GDRDMA cnode7-009:270313:271171 [5] NCCL INFO Channel 01/0 : 13[5] -> 5[5] [send] via NET/IB/6/GDRDMA cnode7-009:270313:271171 [5] NCCL INFO Channel 02/0 : 13[5] -> 5[5] [send] via NET/IB/6/GDRDMA cnode7-009:270313:271171 [5] NCCL INFO Channel 03/0 : 13[5] -> 5[5] [send] via NET/IB/6/GDRDMA cnode7-009:270313:271171 [5] NCCL INFO Channel 04/0 : 13[5] -> 5[5] [send] via NET/IB/6/GDRDMA cnode7-009:270313:271171 [5] NCCL INFO Channel 06/0 : 13[5] -> 5[5] [send] via NET/IB/6/GDRDMA cnode7-009:270313:271171 [5] NCCL INFO Channel 07/0 : 13[5] -> 5[5] [send] via NET/IB/6/GDRDMA cnode7-009:270313:271171 [5] NCCL INFO Channel 08/0 : 13[5] -> 5[5] [send] via NET/IB/6/GDRDMA cnode7-009:270313:271171 [5] NCCL INFO Channel 09/0 : 13[5] -> 5[5] [send] via NET/IB/6/GDRDMA cnode7-009:270313:271171 [5] NCCL INFO Channel 10/0 : 13[5] -> 5[5] [send] via NET/IB/6/GDRDMA cnode7-009:270313:271171 [5] NCCL INFO Channel 11/0 : 13[5] -> 5[5] [send] via NET/IB/6/GDRDMA cnode7-009:270313:271171 [5] NCCL INFO Channel 12/0 : 13[5] -> 5[5] [send] via NET/IB/6/GDRDMA cnode7-009:270313:271171 [5] NCCL INFO Channel 14/0 : 13[5] -> 5[5] [send] via NET/IB/6/GDRDMA cnode7-009:270313:271171 [5] NCCL INFO Channel 15/0 : 13[5] -> 5[5] [send] via NET/IB/6/GDRDMA cnode7-008:628127:628996 [4] NCCL INFO Channel 09/0 : 12[4] -> 4[4] [receive] via NET/IB/4/GDRDMA cnode7-008:628127:628996 [4] NCCL INFO Channel 10/0 : 12[4] -> 4[4] [receive] via NET/IB/4/GDRDMA cnode7-008:628127:628996 [4] NCCL INFO Channel 11/0 : 12[4] -> 4[4] [receive] via NET/IB/4/GDRDMA cnode7-008:628127:628996 [4] NCCL INFO Channel 13/0 : 12[4] -> 4[4] [receive] via NET/IB/4/GDRDMA cnode7-008:628127:628996 [4] NCCL INFO Channel 14/0 : 12[4] -> 4[4] [receive] via NET/IB/4/GDRDMA cnode7-008:628127:628996 [4] NCCL INFO Channel 15/0 : 12[4] -> 4[4] [receive] via NET/IB/4/GDRDMA cnode7-008:628127:628996 [4] NCCL INFO Channel 00/0 : 4[4] -> 12[4] [send] via NET/IB/4/GDRDMA cnode7-008:628127:628996 [4] NCCL INFO Channel 01/0 : 4[4] -> 12[4] [send] via NET/IB/4/GDRDMA cnode7-008:628127:628996 [4] NCCL INFO Channel 02/0 : 4[4] -> 12[4] [send] via NET/IB/4/GDRDMA cnode7-008:628127:628996 [4] NCCL INFO Channel 03/0 : 4[4] -> 12[4] [send] via NET/IB/4/GDRDMA cnode7-008:628127:628996 [4] NCCL INFO Channel 06/0 : 4[4] -> 12[4] [send] via NET/IB/4/GDRDMA cnode7-008:628127:628996 [4] NCCL INFO Channel 07/0 : 4[4] -> 12[4] [send] via NET/IB/4/GDRDMA cnode7-008:628127:628996 [4] NCCL INFO Channel 08/0 : 4[4] -> 12[4] [send] via NET/IB/4/GDRDMA cnode7-008:628127:628996 [4] NCCL INFO Channel 09/0 : 4[4] -> 12[4] [send] via NET/IB/4/GDRDMA cnode7-008:628127:628996 [4] NCCL INFO Channel 10/0 : 4[4] -> 12[4] [send] via NET/IB/4/GDRDMA cnode7-008:628127:628996 [4] NCCL INFO Channel 11/0 : 4[4] -> 12[4] [send] via NET/IB/4/GDRDMA cnode7-008:628127:628996 [4] NCCL INFO Channel 14/0 : 4[4] -> 12[4] [send] via NET/IB/4/GDRDMA cnode7-008:628127:628996 [4] NCCL INFO Channel 15/0 : 4[4] -> 12[4] [send] via NET/IB/4/GDRDMA cnode7-008:628129:628991 [6] NCCL INFO Channel 09/0 : 14[6] -> 6[6] [receive] via NET/IB/7/GDRDMA cnode7-008:628129:628991 [6] NCCL INFO Channel 10/0 : 14[6] -> 6[6] [receive] via NET/IB/7/GDRDMA cnode7-008:628129:628991 [6] NCCL INFO Channel 11/0 : 14[6] -> 6[6] [receive] via NET/IB/7/GDRDMA cnode7-008:628129:628991 [6] NCCL INFO Channel 12/0 : 14[6] -> 6[6] [receive] via NET/IB/7/GDRDMA cnode7-008:628129:628991 [6] NCCL INFO Channel 13/0 : 14[6] -> 6[6] [receive] via NET/IB/7/GDRDMA cnode7-008:628129:628991 [6] NCCL INFO Channel 15/0 : 14[6] -> 6[6] [receive] via NET/IB/7/GDRDMA cnode7-008:628129:628991 [6] NCCL INFO Channel 00/0 : 6[6] -> 14[6] [send] via NET/IB/7/GDRDMA cnode7-008:628129:628991 [6] NCCL INFO Channel 01/0 : 6[6] -> 14[6] [send] via NET/IB/7/GDRDMA cnode7-008:628129:628991 [6] NCCL INFO Channel 02/0 : 6[6] -> 14[6] [send] via NET/IB/7/GDRDMA cnode7-008:628129:628991 [6] NCCL INFO Channel 03/0 : 6[6] -> 14[6] [send] via NET/IB/7/GDRDMA cnode7-008:628129:628991 [6] NCCL INFO Channel 04/0 : 6[6] -> 14[6] [send] via NET/IB/7/GDRDMA cnode7-008:628129:628991 [6] NCCL INFO Channel 05/0 : 6[6] -> 14[6] [send] via NET/IB/7/GDRDMA cnode7-008:628129:628991 [6] NCCL INFO Channel 08/0 : 6[6] -> 14[6] [send] via NET/IB/7/GDRDMA cnode7-008:628129:628991 [6] NCCL INFO Channel 09/0 : 6[6] -> 14[6] [send] via NET/IB/7/GDRDMA cnode7-008:628129:628991 [6] NCCL INFO Channel 10/0 : 6[6] -> 14[6] [send] via NET/IB/7/GDRDMA cnode7-008:628129:628991 [6] NCCL INFO Channel 11/0 : 6[6] -> 14[6] [send] via NET/IB/7/GDRDMA cnode7-008:628129:628991 [6] NCCL INFO Channel 12/0 : 6[6] -> 14[6] [send] via NET/IB/7/GDRDMA cnode7-008:628129:628991 [6] NCCL INFO Channel 13/0 : 6[6] -> 14[6] [send] via NET/IB/7/GDRDMA cnode7-009:270315:271168 [7] NCCL INFO Channel 10/0 : 7[7] -> 15[7] [receive] via NET/IB/8/GDRDMA cnode7-009:270315:271168 [7] NCCL INFO Channel 11/0 : 7[7] -> 15[7] [receive] via NET/IB/8/GDRDMA cnode7-009:270315:271168 [7] NCCL INFO Channel 12/0 : 7[7] -> 15[7] [receive] via NET/IB/8/GDRDMA cnode7-009:270315:271168 [7] NCCL INFO Channel 13/0 : 7[7] -> 15[7] [receive] via NET/IB/8/GDRDMA cnode7-009:270315:271168 [7] NCCL INFO Channel 00/0 : 15[7] -> 7[7] [send] via NET/IB/8/GDRDMA cnode7-009:270315:271168 [7] NCCL INFO Channel 01/0 : 15[7] -> 7[7] [send] via NET/IB/8/GDRDMA cnode7-009:270315:271168 [7] NCCL INFO Channel 02/0 : 15[7] -> 7[7] [send] via NET/IB/8/GDRDMA cnode7-009:270315:271168 [7] NCCL INFO Channel 03/0 : 15[7] -> 7[7] [send] via NET/IB/8/GDRDMA cnode7-009:270315:271168 [7] NCCL INFO Channel 04/0 : 15[7] -> 7[7] [send] via NET/IB/8/GDRDMA cnode7-009:270315:271168 [7] NCCL INFO Channel 05/0 : 15[7] -> 7[7] [send] via NET/IB/8/GDRDMA cnode7-009:270315:271168 [7] NCCL INFO Channel 06/0 : 15[7] -> 7[7] [send] via NET/IB/8/GDRDMA cnode7-009:270315:271168 [7] NCCL INFO Channel 08/0 : 15[7] -> 7[7] [send] via NET/IB/8/GDRDMA cnode7-009:270315:271168 [7] NCCL INFO Channel 09/0 : 15[7] -> 7[7] [send] via NET/IB/8/GDRDMA cnode7-009:270315:271168 [7] NCCL INFO Channel 10/0 : 15[7] -> 7[7] [send] via NET/IB/8/GDRDMA cnode7-009:270315:271168 [7] NCCL INFO Channel 11/0 : 15[7] -> 7[7] [send] via NET/IB/8/GDRDMA cnode7-009:270315:271168 [7] NCCL INFO Channel 12/0 : 15[7] -> 7[7] [send] via NET/IB/8/GDRDMA cnode7-009:270315:271168 [7] NCCL INFO Channel 13/0 : 15[7] -> 7[7] [send] via NET/IB/8/GDRDMA cnode7-009:270315:271168 [7] NCCL INFO Channel 14/0 : 15[7] -> 7[7] [send] via NET/IB/8/GDRDMA cnode7-009:270314:271132 [6] NCCL INFO Channel 10/0 : 6[6] -> 14[6] [receive] via NET/IB/7/GDRDMA cnode7-009:270314:271132 [6] NCCL INFO Channel 11/0 : 6[6] -> 14[6] [receive] via NET/IB/7/GDRDMA cnode7-009:270314:271132 [6] NCCL INFO Channel 12/0 : 6[6] -> 14[6] [receive] via NET/IB/7/GDRDMA cnode7-009:270314:271132 [6] NCCL INFO Channel 13/0 : 6[6] -> 14[6] [receive] via NET/IB/7/GDRDMA cnode7-009:270314:271132 [6] NCCL INFO Channel 00/0 : 14[6] -> 6[6] [send] via NET/IB/7/GDRDMA cnode7-009:270314:271132 [6] NCCL INFO Channel 01/0 : 14[6] -> 6[6] [send] via NET/IB/7/GDRDMA cnode7-009:270314:271132 [6] NCCL INFO Channel 02/0 : 14[6] -> 6[6] [send] via NET/IB/7/GDRDMA cnode7-009:270314:271132 [6] NCCL INFO Channel 03/0 : 14[6] -> 6[6] [send] via NET/IB/7/GDRDMA cnode7-009:270314:271132 [6] NCCL INFO Channel 04/0 : 14[6] -> 6[6] [send] via NET/IB/7/GDRDMA cnode7-009:270314:271132 [6] NCCL INFO Channel 05/0 : 14[6] -> 6[6] [send] via NET/IB/7/GDRDMA cnode7-009:270314:271132 [6] NCCL INFO Channel 07/0 : 14[6] -> 6[6] [send] via NET/IB/7/GDRDMA cnode7-009:270314:271132 [6] NCCL INFO Channel 08/0 : 14[6] -> 6[6] [send] via NET/IB/7/GDRDMA cnode7-009:270314:271132 [6] NCCL INFO Channel 09/0 : 14[6] -> 6[6] [send] via NET/IB/7/GDRDMA cnode7-009:270314:271132 [6] NCCL INFO Channel 10/0 : 14[6] -> 6[6] [send] via NET/IB/7/GDRDMA cnode7-009:270314:271132 [6] NCCL INFO Channel 11/0 : 14[6] -> 6[6] [send] via NET/IB/7/GDRDMA cnode7-009:270314:271132 [6] NCCL INFO Channel 12/0 : 14[6] -> 6[6] [send] via NET/IB/7/GDRDMA cnode7-009:270314:271132 [6] NCCL INFO Channel 13/0 : 14[6] -> 6[6] [send] via NET/IB/7/GDRDMA cnode7-009:270314:271132 [6] NCCL INFO Channel 15/0 : 14[6] -> 6[6] [send] via NET/IB/7/GDRDMA cnode7-009:270312:271209 [4] NCCL INFO Channel 10/0 : 4[4] -> 12[4] [receive] via NET/IB/4/GDRDMA cnode7-009:270312:271209 [4] NCCL INFO Channel 11/0 : 4[4] -> 12[4] [receive] via NET/IB/4/GDRDMA cnode7-009:270312:271209 [4] NCCL INFO Channel 14/0 : 4[4] -> 12[4] [receive] via NET/IB/4/GDRDMA cnode7-009:270312:271209 [4] NCCL INFO Channel 15/0 : 4[4] -> 12[4] [receive] via NET/IB/4/GDRDMA cnode7-009:270312:271209 [4] NCCL INFO Channel 00/0 : 12[4] -> 4[4] [send] via NET/IB/4/GDRDMA cnode7-009:270312:271209 [4] NCCL INFO Channel 01/0 : 12[4] -> 4[4] [send] via NET/IB/4/GDRDMA cnode7-009:270312:271209 [4] NCCL INFO Channel 02/0 : 12[4] -> 4[4] [send] via NET/IB/4/GDRDMA cnode7-009:270312:271209 [4] NCCL INFO Channel 03/0 : 12[4] -> 4[4] [send] via NET/IB/4/GDRDMA cnode7-009:270312:271209 [4] NCCL INFO Channel 05/0 : 12[4] -> 4[4] [send] via NET/IB/4/GDRDMA cnode7-009:270312:271209 [4] NCCL INFO Channel 06/0 : 12[4] -> 4[4] [send] via NET/IB/4/GDRDMA cnode7-009:270312:271209 [4] NCCL INFO Channel 07/0 : 12[4] -> 4[4] [send] via NET/IB/4/GDRDMA cnode7-009:270312:271209 [4] NCCL INFO Channel 08/0 : 12[4] -> 4[4] [send] via NET/IB/4/GDRDMA cnode7-009:270312:271209 [4] NCCL INFO Channel 09/0 : 12[4] -> 4[4] [send] via NET/IB/4/GDRDMA cnode7-009:270312:271209 [4] NCCL INFO Channel 10/0 : 12[4] -> 4[4] [send] via NET/IB/4/GDRDMA cnode7-009:270312:271209 [4] NCCL INFO Channel 11/0 : 12[4] -> 4[4] [send] via NET/IB/4/GDRDMA cnode7-009:270312:271209 [4] NCCL INFO Channel 13/0 : 12[4] -> 4[4] [send] via NET/IB/4/GDRDMA cnode7-009:270312:271209 [4] NCCL INFO Channel 14/0 : 12[4] -> 4[4] [send] via NET/IB/4/GDRDMA cnode7-009:270312:271209 [4] NCCL INFO Channel 15/0 : 12[4] -> 4[4] [send] via NET/IB/4/GDRDMA cnode7-009:270311:271117 [3] NCCL INFO Channel 12/0 : 3[3] -> 11[3] [receive] via NET/IB/3/GDRDMA cnode7-009:270311:271117 [3] NCCL INFO Channel 13/0 : 3[3] -> 11[3] [receive] via NET/IB/3/GDRDMA cnode7-009:270311:271117 [3] NCCL INFO Channel 14/0 : 3[3] -> 11[3] [receive] via NET/IB/3/GDRDMA cnode7-009:270311:271117 [3] NCCL INFO Channel 15/0 : 3[3] -> 11[3] [receive] via NET/IB/3/GDRDMA cnode7-009:270311:271117 [3] NCCL INFO Channel 00/0 : 11[3] -> 3[3] [send] via NET/IB/3/GDRDMA cnode7-009:270311:271117 [3] NCCL INFO Channel 01/0 : 11[3] -> 3[3] [send] via NET/IB/3/GDRDMA cnode7-009:270311:271117 [3] NCCL INFO Channel 02/0 : 11[3] -> 3[3] [send] via NET/IB/3/GDRDMA cnode7-009:270311:271117 [3] NCCL INFO Channel 04/0 : 11[3] -> 3[3] [send] via NET/IB/3/GDRDMA cnode7-009:270311:271117 [3] NCCL INFO Channel 05/0 : 11[3] -> 3[3] [send] via NET/IB/3/GDRDMA cnode7-009:270311:271117 [3] NCCL INFO Channel 06/0 : 11[3] -> 3[3] [send] via NET/IB/3/GDRDMA cnode7-009:270311:271117 [3] NCCL INFO Channel 07/0 : 11[3] -> 3[3] [send] via NET/IB/3/GDRDMA cnode7-009:270311:271117 [3] NCCL INFO Channel 08/0 : 11[3] -> 3[3] [send] via NET/IB/3/GDRDMA cnode7-009:270311:271117 [3] NCCL INFO Channel 09/0 : 11[3] -> 3[3] [send] via NET/IB/3/GDRDMA cnode7-009:270311:271117 [3] NCCL INFO Channel 10/0 : 11[3] -> 3[3] [send] via NET/IB/3/GDRDMA cnode7-009:270311:271117 [3] NCCL INFO Channel 12/0 : 11[3] -> 3[3] [send] via NET/IB/3/GDRDMA cnode7-009:270311:271117 [3] NCCL INFO Channel 13/0 : 11[3] -> 3[3] [send] via NET/IB/3/GDRDMA cnode7-009:270311:271117 [3] NCCL INFO Channel 14/0 : 11[3] -> 3[3] [send] via NET/IB/3/GDRDMA cnode7-009:270311:271117 [3] NCCL INFO Channel 15/0 : 11[3] -> 3[3] [send] via NET/IB/3/GDRDMA cnode7-009:270309:271118 [1] NCCL INFO Channel 12/0 : 1[1] -> 9[1] [receive] via NET/IB/1/GDRDMA cnode7-009:270309:271118 [1] NCCL INFO Channel 13/0 : 1[1] -> 9[1] [receive] via NET/IB/1/GDRDMA cnode7-009:270309:271118 [1] NCCL INFO Channel 14/0 : 1[1] -> 9[1] [receive] via NET/IB/1/GDRDMA cnode7-009:270309:271118 [1] NCCL INFO Channel 15/0 : 1[1] -> 9[1] [receive] via NET/IB/1/GDRDMA cnode7-009:270309:271118 [1] NCCL INFO Channel 00/0 : 9[1] -> 1[1] [send] via NET/IB/1/GDRDMA cnode7-009:270309:271118 [1] NCCL INFO Channel 02/0 : 9[1] -> 1[1] [send] via NET/IB/1/GDRDMA cnode7-009:270309:271118 [1] NCCL INFO Channel 03/0 : 9[1] -> 1[1] [send] via NET/IB/1/GDRDMA cnode7-009:270309:271118 [1] NCCL INFO Channel 04/0 : 9[1] -> 1[1] [send] via NET/IB/1/GDRDMA cnode7-009:270309:271118 [1] NCCL INFO Channel 05/0 : 9[1] -> 1[1] [send] via NET/IB/1/GDRDMA cnode7-009:270309:271118 [1] NCCL INFO Channel 06/0 : 9[1] -> 1[1] [send] via NET/IB/1/GDRDMA cnode7-009:270309:271118 [1] NCCL INFO Channel 07/0 : 9[1] -> 1[1] [send] via NET/IB/1/GDRDMA cnode7-009:270309:271118 [1] NCCL INFO Channel 08/0 : 9[1] -> 1[1] [send] via NET/IB/1/GDRDMA cnode7-009:270309:271118 [1] NCCL INFO Channel 10/0 : 9[1] -> 1[1] [send] via NET/IB/1/GDRDMA cnode7-009:270309:271118 [1] NCCL INFO Channel 11/0 : 9[1] -> 1[1] [send] via NET/IB/1/GDRDMA cnode7-009:270309:271118 [1] NCCL INFO Channel 12/0 : 9[1] -> 1[1] [send] via NET/IB/1/GDRDMA cnode7-009:270309:271118 [1] NCCL INFO Channel 13/0 : 9[1] -> 1[1] [send] via NET/IB/1/GDRDMA cnode7-009:270309:271118 [1] NCCL INFO Channel 14/0 : 9[1] -> 1[1] [send] via NET/IB/1/GDRDMA cnode7-009:270309:271118 [1] NCCL INFO Channel 15/0 : 9[1] -> 1[1] [send] via NET/IB/1/GDRDMA cnode7-008:628125:628997 [2] NCCL INFO Channel 09/0 : 10[2] -> 2[2] [receive] via NET/IB/2/GDRDMA cnode7-008:628125:628997 [2] NCCL INFO Channel 11/0 : 10[2] -> 2[2] [receive] via NET/IB/2/GDRDMA cnode7-008:628125:628997 [2] NCCL INFO Channel 12/0 : 10[2] -> 2[2] [receive] via NET/IB/2/GDRDMA cnode7-008:628125:628997 [2] NCCL INFO Channel 13/0 : 10[2] -> 2[2] [receive] via NET/IB/2/GDRDMA cnode7-008:628125:628997 [2] NCCL INFO Channel 14/0 : 10[2] -> 2[2] [receive] via NET/IB/2/GDRDMA cnode7-008:628125:628997 [2] NCCL INFO Channel 15/0 : 10[2] -> 2[2] [receive] via NET/IB/2/GDRDMA cnode7-008:628125:628997 [2] NCCL INFO Channel 00/0 : 2[2] -> 10[2] [send] via NET/IB/2/GDRDMA cnode7-008:628125:628997 [2] NCCL INFO Channel 01/0 : 2[2] -> 10[2] [send] via NET/IB/2/GDRDMA cnode7-008:628125:628997 [2] NCCL INFO Channel 04/0 : 2[2] -> 10[2] [send] via NET/IB/2/GDRDMA cnode7-008:628125:628997 [2] NCCL INFO Channel 05/0 : 2[2] -> 10[2] [send] via NET/IB/2/GDRDMA cnode7-008:628125:628997 [2] NCCL INFO Channel 06/0 : 2[2] -> 10[2] [send] via NET/IB/2/GDRDMA cnode7-008:628125:628997 [2] NCCL INFO Channel 07/0 : 2[2] -> 10[2] [send] via NET/IB/2/GDRDMA cnode7-008:628125:628997 [2] NCCL INFO Channel 08/0 : 2[2] -> 10[2] [send] via NET/IB/2/GDRDMA cnode7-008:628125:628997 [2] NCCL INFO Channel 09/0 : 2[2] -> 10[2] [send] via NET/IB/2/GDRDMA cnode7-008:628125:628997 [2] NCCL INFO Channel 12/0 : 2[2] -> 10[2] [send] via NET/IB/2/GDRDMA cnode7-008:628125:628997 [2] NCCL INFO Channel 13/0 : 2[2] -> 10[2] [send] via NET/IB/2/GDRDMA cnode7-008:628125:628997 [2] NCCL INFO Channel 14/0 : 2[2] -> 10[2] [send] via NET/IB/2/GDRDMA cnode7-008:628125:628997 [2] NCCL INFO Channel 15/0 : 2[2] -> 10[2] [send] via NET/IB/2/GDRDMA cnode7-008:628124:628983 [1] NCCL INFO Channel 10/0 : 9[1] -> 1[1] [receive] via NET/IB/1/GDRDMA cnode7-008:628124:628983 [1] NCCL INFO Channel 11/0 : 9[1] -> 1[1] [receive] via NET/IB/1/GDRDMA cnode7-008:628124:628983 [1] NCCL INFO Channel 12/0 : 9[1] -> 1[1] [receive] via NET/IB/1/GDRDMA cnode7-008:628124:628983 [1] NCCL INFO Channel 13/0 : 9[1] -> 1[1] [receive] via NET/IB/1/GDRDMA cnode7-008:628124:628983 [1] NCCL INFO Channel 14/0 : 9[1] -> 1[1] [receive] via NET/IB/1/GDRDMA cnode7-008:628124:628983 [1] NCCL INFO Channel 15/0 : 9[1] -> 1[1] [receive] via NET/IB/1/GDRDMA cnode7-008:628124:628983 [1] NCCL INFO Channel 02/0 : 1[1] -> 9[1] [send] via NET/IB/1/GDRDMA cnode7-008:628124:628983 [1] NCCL INFO Channel 03/0 : 1[1] -> 9[1] [send] via NET/IB/1/GDRDMA cnode7-008:628124:628983 [1] NCCL INFO Channel 04/0 : 1[1] -> 9[1] [send] via NET/IB/1/GDRDMA cnode7-008:628124:628983 [1] NCCL INFO Channel 05/0 : 1[1] -> 9[1] [send] via NET/IB/1/GDRDMA cnode7-008:628124:628983 [1] NCCL INFO Channel 06/0 : 1[1] -> 9[1] [send] via NET/IB/1/GDRDMA cnode7-008:628124:628983 [1] NCCL INFO Channel 07/0 : 1[1] -> 9[1] [send] via NET/IB/1/GDRDMA cnode7-008:628124:628983 [1] NCCL INFO Channel 10/0 : 1[1] -> 9[1] [send] via NET/IB/1/GDRDMA cnode7-008:628124:628983 [1] NCCL INFO Channel 11/0 : 1[1] -> 9[1] [send] via NET/IB/1/GDRDMA cnode7-008:628124:628983 [1] NCCL INFO Channel 12/0 : 1[1] -> 9[1] [send] via NET/IB/1/GDRDMA cnode7-008:628124:628983 [1] NCCL INFO Channel 13/0 : 1[1] -> 9[1] [send] via NET/IB/1/GDRDMA cnode7-008:628124:628983 [1] NCCL INFO Channel 14/0 : 1[1] -> 9[1] [send] via NET/IB/1/GDRDMA cnode7-008:628124:628983 [1] NCCL INFO Channel 15/0 : 1[1] -> 9[1] [send] via NET/IB/1/GDRDMA cnode7-008:628123:628980 [0] NCCL INFO Channel 10/0 : 8[0] -> 0[0] [receive] via NET/IB/0/GDRDMA cnode7-008:628123:628980 [0] NCCL INFO Channel 11/0 : 8[0] -> 0[0] [receive] via NET/IB/0/GDRDMA cnode7-008:628123:628980 [0] NCCL INFO Channel 12/0 : 8[0] -> 0[0] [receive] via NET/IB/0/GDRDMA cnode7-008:628123:628980 [0] NCCL INFO Channel 13/0 : 8[0] -> 0[0] [receive] via NET/IB/0/GDRDMA cnode7-008:628123:628980 [0] NCCL INFO Channel 14/0 : 8[0] -> 0[0] [receive] via NET/IB/0/GDRDMA cnode7-008:628123:628980 [0] NCCL INFO Channel 15/0 : 8[0] -> 0[0] [receive] via NET/IB/0/GDRDMA cnode7-008:628123:628980 [0] NCCL INFO Channel 02/0 : 0[0] -> 8[0] [send] via NET/IB/0/GDRDMA cnode7-008:628123:628980 [0] NCCL INFO Channel 03/0 : 0[0] -> 8[0] [send] via NET/IB/0/GDRDMA cnode7-008:628123:628980 [0] NCCL INFO Channel 04/0 : 0[0] -> 8[0] [send] via NET/IB/0/GDRDMA cnode7-008:628123:628980 [0] NCCL INFO Channel 05/0 : 0[0] -> 8[0] [send] via NET/IB/0/GDRDMA cnode7-008:628123:628980 [0] NCCL INFO Channel 06/0 : 0[0] -> 8[0] [send] via NET/IB/0/GDRDMA cnode7-008:628123:628980 [0] NCCL INFO Channel 07/0 : 0[0] -> 8[0] [send] via NET/IB/0/GDRDMA cnode7-008:628123:628980 [0] NCCL INFO Channel 10/0 : 0[0] -> 8[0] [send] via NET/IB/0/GDRDMA cnode7-008:628123:628980 [0] NCCL INFO Channel 11/0 : 0[0] -> 8[0] [send] via NET/IB/0/GDRDMA cnode7-008:628123:628980 [0] NCCL INFO Channel 12/0 : 0[0] -> 8[0] [send] via NET/IB/0/GDRDMA cnode7-008:628123:628980 [0] NCCL INFO Channel 13/0 : 0[0] -> 8[0] [send] via NET/IB/0/GDRDMA cnode7-008:628123:628980 [0] NCCL INFO Channel 14/0 : 0[0] -> 8[0] [send] via NET/IB/0/GDRDMA cnode7-008:628123:628980 [0] NCCL INFO Channel 15/0 : 0[0] -> 8[0] [send] via NET/IB/0/GDRDMA cnode7-009:270310:271224 [2] NCCL INFO Channel 12/0 : 2[2] -> 10[2] [receive] via NET/IB/2/GDRDMA cnode7-009:270310:271224 [2] NCCL INFO Channel 13/0 : 2[2] -> 10[2] [receive] via NET/IB/2/GDRDMA cnode7-009:270310:271224 [2] NCCL INFO Channel 14/0 : 2[2] -> 10[2] [receive] via NET/IB/2/GDRDMA cnode7-009:270310:271224 [2] NCCL INFO Channel 15/0 : 2[2] -> 10[2] [receive] via NET/IB/2/GDRDMA cnode7-009:270310:271224 [2] NCCL INFO Channel 00/0 : 10[2] -> 2[2] [send] via NET/IB/2/GDRDMA cnode7-009:270310:271224 [2] NCCL INFO Channel 01/0 : 10[2] -> 2[2] [send] via NET/IB/2/GDRDMA cnode7-009:270310:271224 [2] NCCL INFO Channel 03/0 : 10[2] -> 2[2] [send] via NET/IB/2/GDRDMA cnode7-009:270310:271224 [2] NCCL INFO Channel 04/0 : 10[2] -> 2[2] [send] via NET/IB/2/GDRDMA cnode7-009:270310:271224 [2] NCCL INFO Channel 05/0 : 10[2] -> 2[2] [send] via NET/IB/2/GDRDMA cnode7-009:270310:271224 [2] NCCL INFO Channel 06/0 : 10[2] -> 2[2] [send] via NET/IB/2/GDRDMA cnode7-009:270310:271224 [2] NCCL INFO Channel 07/0 : 10[2] -> 2[2] [send] via NET/IB/2/GDRDMA cnode7-009:270310:271224 [2] NCCL INFO Channel 08/0 : 10[2] -> 2[2] [send] via NET/IB/2/GDRDMA cnode7-009:270310:271224 [2] NCCL INFO Channel 09/0 : 10[2] -> 2[2] [send] via NET/IB/2/GDRDMA cnode7-009:270310:271224 [2] NCCL INFO Channel 11/0 : 10[2] -> 2[2] [send] via NET/IB/2/GDRDMA cnode7-009:270310:271224 [2] NCCL INFO Channel 12/0 : 10[2] -> 2[2] [send] via NET/IB/2/GDRDMA cnode7-009:270310:271224 [2] NCCL INFO Channel 13/0 : 10[2] -> 2[2] [send] via NET/IB/2/GDRDMA cnode7-009:270310:271224 [2] NCCL INFO Channel 14/0 : 10[2] -> 2[2] [send] via NET/IB/2/GDRDMA cnode7-009:270310:271224 [2] NCCL INFO Channel 15/0 : 10[2] -> 2[2] [send] via NET/IB/2/GDRDMA cnode7-008:628130:628985 [7] NCCL INFO Channel 09/0 : 15[7] -> 7[7] [receive] via NET/IB/8/GDRDMA cnode7-008:628130:628985 [7] NCCL INFO Channel 10/0 : 15[7] -> 7[7] [receive] via NET/IB/8/GDRDMA cnode7-008:628130:628985 [7] NCCL INFO Channel 11/0 : 15[7] -> 7[7] [receive] via NET/IB/8/GDRDMA cnode7-008:628130:628985 [7] NCCL INFO Channel 12/0 : 15[7] -> 7[7] [receive] via NET/IB/8/GDRDMA cnode7-008:628130:628985 [7] NCCL INFO Channel 13/0 : 15[7] -> 7[7] [receive] via NET/IB/8/GDRDMA cnode7-008:628130:628985 [7] NCCL INFO Channel 14/0 : 15[7] -> 7[7] [receive] via NET/IB/8/GDRDMA cnode7-008:628130:628985 [7] NCCL INFO Channel 00/0 : 7[7] -> 15[7] [send] via NET/IB/8/GDRDMA cnode7-008:628130:628985 [7] NCCL INFO Channel 01/0 : 7[7] -> 15[7] [send] via NET/IB/8/GDRDMA cnode7-008:628130:628985 [7] NCCL INFO Channel 02/0 : 7[7] -> 15[7] [send] via NET/IB/8/GDRDMA cnode7-008:628130:628985 [7] NCCL INFO Channel 03/0 : 7[7] -> 15[7] [send] via NET/IB/8/GDRDMA cnode7-008:628130:628985 [7] NCCL INFO Channel 04/0 : 7[7] -> 15[7] [send] via NET/IB/8/GDRDMA cnode7-008:628130:628985 [7] NCCL INFO Channel 05/0 : 7[7] -> 15[7] [send] via NET/IB/8/GDRDMA cnode7-008:628130:628985 [7] NCCL INFO Channel 08/0 : 7[7] -> 15[7] [send] via NET/IB/8/GDRDMA cnode7-008:628130:628985 [7] NCCL INFO Channel 09/0 : 7[7] -> 15[7] [send] via NET/IB/8/GDRDMA cnode7-008:628130:628985 [7] NCCL INFO Channel 10/0 : 7[7] -> 15[7] [send] via NET/IB/8/GDRDMA cnode7-008:628130:628985 [7] NCCL INFO Channel 11/0 : 7[7] -> 15[7] [send] via NET/IB/8/GDRDMA cnode7-008:628130:628985 [7] NCCL INFO Channel 12/0 : 7[7] -> 15[7] [send] via NET/IB/8/GDRDMA cnode7-008:628130:628985 [7] NCCL INFO Channel 13/0 : 7[7] -> 15[7] [send] via NET/IB/8/GDRDMA cnode7-008:628126:628984 [3] NCCL INFO Channel 09/0 : 11[3] -> 3[3] [receive] via NET/IB/3/GDRDMA cnode7-008:628126:628984 [3] NCCL INFO Channel 10/0 : 11[3] -> 3[3] [receive] via NET/IB/3/GDRDMA cnode7-008:628126:628984 [3] NCCL INFO Channel 12/0 : 11[3] -> 3[3] [receive] via NET/IB/3/GDRDMA cnode7-008:628126:628984 [3] NCCL INFO Channel 13/0 : 11[3] -> 3[3] [receive] via NET/IB/3/GDRDMA cnode7-008:628126:628984 [3] NCCL INFO Channel 14/0 : 11[3] -> 3[3] [receive] via NET/IB/3/GDRDMA cnode7-008:628126:628984 [3] NCCL INFO Channel 15/0 : 11[3] -> 3[3] [receive] via NET/IB/3/GDRDMA cnode7-008:628126:628984 [3] NCCL INFO Channel 00/0 : 3[3] -> 11[3] [send] via NET/IB/3/GDRDMA cnode7-008:628126:628984 [3] NCCL INFO Channel 01/0 : 3[3] -> 11[3] [send] via NET/IB/3/GDRDMA cnode7-008:628126:628984 [3] NCCL INFO Channel 04/0 : 3[3] -> 11[3] [send] via NET/IB/3/GDRDMA cnode7-008:628126:628984 [3] NCCL INFO Channel 05/0 : 3[3] -> 11[3] [send] via NET/IB/3/GDRDMA cnode7-008:628126:628984 [3] NCCL INFO Channel 06/0 : 3[3] -> 11[3] [send] via NET/IB/3/GDRDMA cnode7-008:628126:628984 [3] NCCL INFO Channel 07/0 : 3[3] -> 11[3] [send] via NET/IB/3/GDRDMA cnode7-008:628126:628984 [3] NCCL INFO Channel 08/0 : 3[3] -> 11[3] [send] via NET/IB/3/GDRDMA cnode7-008:628126:628984 [3] NCCL INFO Channel 09/0 : 3[3] -> 11[3] [send] via NET/IB/3/GDRDMA cnode7-008:628126:628984 [3] NCCL INFO Channel 12/0 : 3[3] -> 11[3] [send] via NET/IB/3/GDRDMA cnode7-008:628126:628984 [3] NCCL INFO Channel 13/0 : 3[3] -> 11[3] [send] via NET/IB/3/GDRDMA cnode7-008:628126:628984 [3] NCCL INFO Channel 14/0 : 3[3] -> 11[3] [send] via NET/IB/3/GDRDMA cnode7-008:628126:628984 [3] NCCL INFO Channel 15/0 : 3[3] -> 11[3] [send] via NET/IB/3/GDRDMA cnode7-008:628124:628983 [1] NCCL INFO Connected NVLS tree cnode7-008:628124:628983 [1] NCCL INFO threadThresholds 8/8/64 | 128/8/64 | 512 | 512 cnode7-008:628124:628983 [1] NCCL INFO 16 coll channels, 0 collnet channels, 16 nvls channels, 16 p2p channels, 2 p2p channels per peer cnode7-008:628123:628980 [0] NCCL INFO Connected NVLS tree cnode7-008:628123:628980 [0] NCCL INFO threadThresholds 8/8/64 | 128/8/64 | 512 | 512 cnode7-008:628123:628980 [0] NCCL INFO 16 coll channels, 0 collnet channels, 16 nvls channels, 16 p2p channels, 2 p2p channels per peer cnode7-008:628129:628991 [6] NCCL INFO Connected NVLS tree cnode7-008:628129:628991 [6] NCCL INFO threadThresholds 8/8/64 | 128/8/64 | 512 | 512 cnode7-008:628129:628991 [6] NCCL INFO 16 coll channels, 0 collnet channels, 16 nvls channels, 16 p2p channels, 2 p2p channels per peer cnode7-008:628130:628985 [7] NCCL INFO Connected NVLS tree cnode7-008:628130:628985 [7] NCCL INFO threadThresholds 8/8/64 | 128/8/64 | 512 | 512 cnode7-008:628130:628985 [7] NCCL INFO 16 coll channels, 0 collnet channels, 16 nvls channels, 16 p2p channels, 2 p2p channels per peer cnode7-009:270315:271168 [7] NCCL INFO Connected NVLS tree cnode7-009:270315:271168 [7] NCCL INFO threadThresholds 8/8/64 | 128/8/64 | 512 | 512 cnode7-009:270315:271168 [7] NCCL INFO 16 coll channels, 0 collnet channels, 16 nvls channels, 16 p2p channels, 2 p2p channels per peer cnode7-009:270314:271132 [6] NCCL INFO Connected NVLS tree cnode7-009:270314:271132 [6] NCCL INFO threadThresholds 8/8/64 | 128/8/64 | 512 | 512 cnode7-009:270314:271132 [6] NCCL INFO 16 coll channels, 0 collnet channels, 16 nvls channels, 16 p2p channels, 2 p2p channels per peer cnode7-009:270312:271209 [4] NCCL INFO Connected NVLS tree cnode7-009:270312:271209 [4] NCCL INFO threadThresholds 8/8/64 | 128/8/64 | 512 | 512 cnode7-009:270312:271209 [4] NCCL INFO 16 coll channels, 0 collnet channels, 16 nvls channels, 16 p2p channels, 2 p2p channels per peer cnode7-008:628125:628997 [2] NCCL INFO Connected NVLS tree cnode7-008:628125:628997 [2] NCCL INFO threadThresholds 8/8/64 | 128/8/64 | 512 | 512 cnode7-008:628125:628997 [2] NCCL INFO 16 coll channels, 0 collnet channels, 16 nvls channels, 16 p2p channels, 2 p2p channels per peer cnode7-008:628127:628996 [4] NCCL INFO Connected NVLS tree cnode7-008:628127:628996 [4] NCCL INFO threadThresholds 8/8/64 | 128/8/64 | 512 | 512 cnode7-008:628127:628996 [4] NCCL INFO 16 coll channels, 0 collnet channels, 16 nvls channels, 16 p2p channels, 2 p2p channels per peer cnode7-009:270311:271117 [3] NCCL INFO Connected NVLS tree cnode7-009:270311:271117 [3] NCCL INFO threadThresholds 8/8/64 | 128/8/64 | 512 | 512 cnode7-009:270311:271117 [3] NCCL INFO 16 coll channels, 0 collnet channels, 16 nvls channels, 16 p2p channels, 2 p2p channels per peer cnode7-009:270309:271118 [1] NCCL INFO Connected NVLS tree cnode7-009:270309:271118 [1] NCCL INFO threadThresholds 8/8/64 | 128/8/64 | 512 | 512 cnode7-009:270309:271118 [1] NCCL INFO 16 coll channels, 0 collnet channels, 16 nvls channels, 16 p2p channels, 2 p2p channels per peer cnode7-008:628126:628984 [3] NCCL INFO Connected NVLS tree cnode7-008:628126:628984 [3] NCCL INFO threadThresholds 8/8/64 | 128/8/64 | 512 | 512 cnode7-008:628126:628984 [3] NCCL INFO 16 coll channels, 0 collnet channels, 16 nvls channels, 16 p2p channels, 2 p2p channels per peer cnode7-008:628128:628988 [5] NCCL INFO Connected NVLS tree cnode7-008:628128:628988 [5] NCCL INFO threadThresholds 8/8/64 | 128/8/64 | 512 | 512 cnode7-008:628128:628988 [5] NCCL INFO 16 coll channels, 0 collnet channels, 16 nvls channels, 16 p2p channels, 2 p2p channels per peer cnode7-009:270308:271135 [0] NCCL INFO Connected NVLS tree cnode7-009:270308:271135 [0] NCCL INFO threadThresholds 8/8/64 | 128/8/64 | 512 | 512 cnode7-009:270308:271135 [0] NCCL INFO 16 coll channels, 0 collnet channels, 16 nvls channels, 16 p2p channels, 2 p2p channels per peer cnode7-008:628124:628983 [1] NCCL INFO comm 0x55557c01e980 rank 1 nranks 16 cudaDev 1 nvmlDev 1 busId 43000 commId 0xe3295ea1839cefc9 - Init COMPLETE cnode7-008:628130:628985 [7] NCCL INFO comm 0x55556ca1b270 rank 7 nranks 16 cudaDev 7 nvmlDev 7 busId df000 commId 0xe3295ea1839cefc9 - Init COMPLETE cnode7-008:628129:628991 [6] NCCL INFO comm 0x55557501a8c0 rank 6 nranks 16 cudaDev 6 nvmlDev 6 busId d1000 commId 0xe3295ea1839cefc9 - Init COMPLETE cnode7-008:628127:628996 [4] NCCL INFO comm 0x55558101ada0 rank 4 nranks 16 cudaDev 4 nvmlDev 4 busId 9d000 commId 0xe3295ea1839cefc9 - Init COMPLETE cnode7-008:628126:628984 [3] NCCL INFO comm 0x555566a1a9d0 rank 3 nranks 16 cudaDev 3 nvmlDev 3 busId 61000 commId 0xe3295ea1839cefc9 - Init COMPLETE cnode7-008:628125:628997 [2] NCCL INFO comm 0x55557c41cde0 rank 2 nranks 16 cudaDev 2 nvmlDev 2 busId 52000 commId 0xe3295ea1839cefc9 - Init COMPLETE cnode7-008:628128:628988 [5] NCCL INFO comm 0x555575c23df0 rank 5 nranks 16 cudaDev 5 nvmlDev 5 busId c3000 commId 0xe3295ea1839cefc9 - Init COMPLETE cnode7-008:628123:628980 [0] NCCL INFO comm 0x5555647681e0 rank 0 nranks 16 cudaDev 0 nvmlDev 0 busId 1b000 commId 0xe3295ea1839cefc9 - Init COMPLETE cnode7-009:270310:271224 [2] NCCL INFO Connected NVLS tree cnode7-009:270310:271224 [2] NCCL INFO threadThresholds 8/8/64 | 128/8/64 | 512 | 512 cnode7-009:270310:271224 [2] NCCL INFO 16 coll channels, 0 collnet channels, 16 nvls channels, 16 p2p channels, 2 p2p channels per peer cnode7-009:270313:271171 [5] NCCL INFO Connected NVLS tree cnode7-009:270313:271171 [5] NCCL INFO threadThresholds 8/8/64 | 128/8/64 | 512 | 512 cnode7-009:270313:271171 [5] NCCL INFO 16 coll channels, 0 collnet channels, 16 nvls channels, 16 p2p channels, 2 p2p channels per peer cnode7-009:270315:271168 [7] NCCL INFO comm 0x555561a1aca0 rank 15 nranks 16 cudaDev 7 nvmlDev 7 busId df000 commId 0xe3295ea1839cefc9 - Init COMPLETE cnode7-009:270313:271171 [5] NCCL INFO comm 0x555560c1ad60 rank 13 nranks 16 cudaDev 5 nvmlDev 5 busId c3000 commId 0xe3295ea1839cefc9 - Init COMPLETE cnode7-009:270314:271132 [6] NCCL INFO comm 0x55557bc1ae80 rank 14 nranks 16 cudaDev 6 nvmlDev 6 busId d1000 commId 0xe3295ea1839cefc9 - Init COMPLETE cnode7-009:270310:271224 [2] NCCL INFO comm 0x555560a14700 rank 10 nranks 16 cudaDev 2 nvmlDev 2 busId 52000 commId 0xe3295ea1839cefc9 - Init COMPLETE cnode7-009:270308:271135 [0] NCCL INFO comm 0x555563d3b5b0 rank 8 nranks 16 cudaDev 0 nvmlDev 0 busId 1b000 commId 0xe3295ea1839cefc9 - Init COMPLETE cnode7-009:270311:271117 [3] NCCL INFO comm 0x555569a227f0 rank 11 nranks 16 cudaDev 3 nvmlDev 3 busId 61000 commId 0xe3295ea1839cefc9 - Init COMPLETE cnode7-009:270309:271118 [1] NCCL INFO comm 0x55558161ad80 rank 9 nranks 16 cudaDev 1 nvmlDev 1 busId 43000 commId 0xe3295ea1839cefc9 - Init COMPLETE cnode7-009:270312:271209 [4] NCCL INFO comm 0x55557261ed20 rank 12 nranks 16 cudaDev 4 nvmlDev 4 busId 9d000 commId 0xe3295ea1839cefc9 - Init COMPLETE [2024-12-10 08:40:08,107] [INFO] [logging.py:129:log_dist] [Rank 0] DeepSpeed Flops Profiler Enabled: False [2024-12-10 08:40:08,118] [INFO] [logging.py:129:log_dist] [Rank 0] Using DeepSpeed Optimizer param name adam as basic optimizer [2024-12-10 08:40:08,118] [INFO] [logging.py:129:log_dist] [Rank 0] Removing param_group that has no 'params' in the basic Optimizer [2024-12-10 08:40:08,151] [INFO] [logging.py:129:log_dist] [Rank 0] DeepSpeed Basic Optimizer = FusedAdam [2024-12-10 08:40:08,151] [INFO] [utils.py:59:is_zero_supported_optimizer] Checking ZeRO support for optimizer=FusedAdam type= [2024-12-10 08:40:08,151] [INFO] [logging.py:129:log_dist] [Rank 0] Creating torch.bfloat16 ZeRO stage 2 optimizer [2024-12-10 08:40:08,151] [INFO] [stage_1_and_2.py:149:__init__] Reduce bucket size 500000000 [2024-12-10 08:40:08,151] [INFO] [stage_1_and_2.py:150:__init__] Allgather bucket size 500000000 [2024-12-10 08:40:08,151] [INFO] [stage_1_and_2.py:151:__init__] CPU Offload: False [2024-12-10 08:40:08,151] [INFO] [stage_1_and_2.py:152:__init__] Round robin gradient partitioning: False [2024-12-10 08:40:09,473] [INFO] [torch_checkpoint_engine.py:27:load] [Torch] Loading checkpoint from exp_owsm/s2t_train_05b_ds_raw_bpe50000/checkpoint_40/40/mp_rank_00_model_states.pt... [2024-12-10 08:40:09,473] [INFO] [torch_checkpoint_engine.py:27:load] [Torch] Loading checkpoint from exp_owsm/s2t_train_05b_ds_raw_bpe50000/checkpoint_40/40/mp_rank_00_model_states.pt... [2024-12-10 08:40:09,473] [INFO] [torch_checkpoint_engine.py:27:load] [Torch] Loading checkpoint from exp_owsm/s2t_train_05b_ds_raw_bpe50000/checkpoint_40/40/mp_rank_00_model_states.pt... [2024-12-10 08:40:09,473] [INFO] [torch_checkpoint_engine.py:27:load] [Torch] Loading checkpoint from exp_owsm/s2t_train_05b_ds_raw_bpe50000/checkpoint_40/40/mp_rank_00_model_states.pt... [2024-12-10 08:40:09,473] [INFO] [torch_checkpoint_engine.py:27:load] [Torch] Loading checkpoint from exp_owsm/s2t_train_05b_ds_raw_bpe50000/checkpoint_40/40/mp_rank_00_model_states.pt... [2024-12-10 08:40:09,473] [INFO] [torch_checkpoint_engine.py:27:load] [Torch] Loading checkpoint from exp_owsm/s2t_train_05b_ds_raw_bpe50000/checkpoint_40/40/mp_rank_00_model_states.pt... [2024-12-10 08:40:09,473] [INFO] [torch_checkpoint_engine.py:27:load] [Torch] Loading checkpoint from exp_owsm/s2t_train_05b_ds_raw_bpe50000/checkpoint_40/40/mp_rank_00_model_states.pt... [2024-12-10 08:40:09,473] [INFO] [torch_checkpoint_engine.py:27:load] [Torch] Loading checkpoint from exp_owsm/s2t_train_05b_ds_raw_bpe50000/checkpoint_40/40/mp_rank_00_model_states.pt... /mnt/home/williamchen/espnet/tools/miniconda/envs/espnet/lib/python3.10/site-packages/deepspeed/runtime/checkpoint_engine/torch_checkpoint_engine.py:28: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature. partition = torch.load(path, map_location=map_location) /mnt/home/williamchen/espnet/tools/miniconda/envs/espnet/lib/python3.10/site-packages/deepspeed/runtime/checkpoint_engine/torch_checkpoint_engine.py:28: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature. partition = torch.load(path, map_location=map_location) /mnt/home/williamchen/espnet/tools/miniconda/envs/espnet/lib/python3.10/site-packages/deepspeed/runtime/checkpoint_engine/torch_checkpoint_engine.py:28: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature. partition = torch.load(path, map_location=map_location) /mnt/home/williamchen/espnet/tools/miniconda/envs/espnet/lib/python3.10/site-packages/deepspeed/runtime/checkpoint_engine/torch_checkpoint_engine.py:28: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature. partition = torch.load(path, map_location=map_location) /mnt/home/williamchen/espnet/tools/miniconda/envs/espnet/lib/python3.10/site-packages/deepspeed/runtime/checkpoint_engine/torch_checkpoint_engine.py:28: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature. partition = torch.load(path, map_location=map_location) /mnt/home/williamchen/espnet/tools/miniconda/envs/espnet/lib/python3.10/site-packages/deepspeed/runtime/checkpoint_engine/torch_checkpoint_engine.py:28: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature. partition = torch.load(path, map_location=map_location) /mnt/home/williamchen/espnet/tools/miniconda/envs/espnet/lib/python3.10/site-packages/deepspeed/runtime/checkpoint_engine/torch_checkpoint_engine.py:28: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature. partition = torch.load(path, map_location=map_location) /mnt/home/williamchen/espnet/tools/miniconda/envs/espnet/lib/python3.10/site-packages/deepspeed/runtime/checkpoint_engine/torch_checkpoint_engine.py:28: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature. partition = torch.load(path, map_location=map_location) [2024-12-10 08:40:09,816] [INFO] [torch_checkpoint_engine.py:27:load] [Torch] Loading checkpoint from exp_owsm/s2t_train_05b_ds_raw_bpe50000/checkpoint_40/40/mp_rank_00_model_states.pt... [2024-12-10 08:40:09,816] [INFO] [torch_checkpoint_engine.py:27:load] [Torch] Loading checkpoint from exp_owsm/s2t_train_05b_ds_raw_bpe50000/checkpoint_40/40/mp_rank_00_model_states.pt... [2024-12-10 08:40:09,816] [INFO] [torch_checkpoint_engine.py:27:load] [Torch] Loading checkpoint from exp_owsm/s2t_train_05b_ds_raw_bpe50000/checkpoint_40/40/mp_rank_00_model_states.pt... [2024-12-10 08:40:09,816] [INFO] [torch_checkpoint_engine.py:27:load] [Torch] Loading checkpoint from exp_owsm/s2t_train_05b_ds_raw_bpe50000/checkpoint_40/40/mp_rank_00_model_states.pt... [2024-12-10 08:40:09,816] [INFO] [torch_checkpoint_engine.py:27:load] [Torch] Loading checkpoint from exp_owsm/s2t_train_05b_ds_raw_bpe50000/checkpoint_40/40/mp_rank_00_model_states.pt... [2024-12-10 08:40:09,816] [INFO] [torch_checkpoint_engine.py:27:load] [Torch] Loading checkpoint from exp_owsm/s2t_train_05b_ds_raw_bpe50000/checkpoint_40/40/mp_rank_00_model_states.pt... [2024-12-10 08:40:09,816] [INFO] [torch_checkpoint_engine.py:27:load] [Torch] Loading checkpoint from exp_owsm/s2t_train_05b_ds_raw_bpe50000/checkpoint_40/40/mp_rank_00_model_states.pt... /mnt/home/williamchen/espnet/tools/miniconda/envs/espnet/lib/python3.10/site-packages/deepspeed/runtime/checkpoint_engine/torch_checkpoint_engine.py:28: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature. partition = torch.load(path, map_location=map_location) /mnt/home/williamchen/espnet/tools/miniconda/envs/espnet/lib/python3.10/site-packages/deepspeed/runtime/checkpoint_engine/torch_checkpoint_engine.py:28: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature. partition = torch.load(path, map_location=map_location) /mnt/home/williamchen/espnet/tools/miniconda/envs/espnet/lib/python3.10/site-packages/deepspeed/runtime/checkpoint_engine/torch_checkpoint_engine.py:28: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature. partition = torch.load(path, map_location=map_location) /mnt/home/williamchen/espnet/tools/miniconda/envs/espnet/lib/python3.10/site-packages/deepspeed/runtime/checkpoint_engine/torch_checkpoint_engine.py:28: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature. partition = torch.load(path, map_location=map_location) /mnt/home/williamchen/espnet/tools/miniconda/envs/espnet/lib/python3.10/site-packages/deepspeed/runtime/checkpoint_engine/torch_checkpoint_engine.py:28: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature. partition = torch.load(path, map_location=map_location) /mnt/home/williamchen/espnet/tools/miniconda/envs/espnet/lib/python3.10/site-packages/deepspeed/runtime/checkpoint_engine/torch_checkpoint_engine.py:28: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature. partition = torch.load(path, map_location=map_location) /mnt/home/williamchen/espnet/tools/miniconda/envs/espnet/lib/python3.10/site-packages/deepspeed/runtime/checkpoint_engine/torch_checkpoint_engine.py:28: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature. partition = torch.load(path, map_location=map_location) [2024-12-10 08:40:10,132] [INFO] [utils.py:781:see_memory_usage] Before initializing optimizer states [2024-12-10 08:40:10,169] [INFO] [utils.py:782:see_memory_usage] MA 1.37 GB Max_MA 1.45 GB CA 1.45 GB Max_CA 1 GB [2024-12-10 08:40:10,169] [INFO] [utils.py:789:see_memory_usage] CPU Virtual Memory: used = 65.53 GB, percent = 3.3% [2024-12-10 08:40:10,349] [INFO] [utils.py:781:see_memory_usage] After initializing optimizer states [2024-12-10 08:40:10,350] [INFO] [utils.py:782:see_memory_usage] MA 1.37 GB Max_MA 1.52 GB CA 1.6 GB Max_CA 2 GB [2024-12-10 08:40:10,350] [INFO] [utils.py:789:see_memory_usage] CPU Virtual Memory: used = 67.23 GB, percent = 3.3% [2024-12-10 08:40:10,350] [INFO] [stage_1_and_2.py:544:__init__] optimizer state initialized [2024-12-10 08:40:10,490] [INFO] [utils.py:781:see_memory_usage] After initializing ZeRO optimizer [2024-12-10 08:40:10,490] [INFO] [utils.py:782:see_memory_usage] MA 1.37 GB Max_MA 1.37 GB CA 1.6 GB Max_CA 2 GB [2024-12-10 08:40:10,491] [INFO] [utils.py:789:see_memory_usage] CPU Virtual Memory: used = 67.56 GB, percent = 3.4% [2024-12-10 08:40:10,492] [INFO] [logging.py:129:log_dist] [Rank 0] DeepSpeed Final Optimizer = DeepSpeedZeroOptimizer [2024-12-10 08:40:10,493] [INFO] [logging.py:129:log_dist] [Rank 0] DeepSpeed using client callable to create LR scheduler [2024-12-10 08:40:10,493] [INFO] [logging.py:129:log_dist] [Rank 0] DeepSpeed LR Scheduler = PiecewiseLinearWarmupLR(warmup_steps_list=[0, 30000, 60000], warmup_lr_list=[0.0, 5e-05, 0.0002]) [2024-12-10 08:40:10,493] [INFO] [logging.py:129:log_dist] [Rank 0] step=0, skipped=0, lr=[np.float64(1.6666666666666667e-09)], mom=[[0.9, 0.98]] [2024-12-10 08:40:10,494] [INFO] [config.py:999:print] DeepSpeedEngine configuration: [2024-12-10 08:40:10,494] [INFO] [config.py:1003:print] activation_checkpointing_config { "partition_activations": false, "contiguous_memory_optimization": false, "cpu_checkpointing": false, "number_checkpoints": null, "synchronize_checkpoint_boundary": false, "profile": false } [2024-12-10 08:40:10,494] [INFO] [config.py:1003:print] aio_config ................... {'block_size': 1048576, 'queue_depth': 8, 'thread_count': 1, 'single_submit': False, 'overlap_events': True, 'use_gds': False} [2024-12-10 08:40:10,494] [INFO] [config.py:1003:print] amp_enabled .................. False [2024-12-10 08:40:10,494] [INFO] [config.py:1003:print] amp_params ................... False [2024-12-10 08:40:10,495] [INFO] [config.py:1003:print] autotuning_config ............ { "enabled": false, "start_step": null, "end_step": null, "metric_path": null, "arg_mappings": null, "metric": "throughput", "model_info": null, "results_dir": "autotuning_results", "exps_dir": "autotuning_exps", "overwrite": true, "fast": true, "start_profile_step": 3, "end_profile_step": 5, "tuner_type": "gridsearch", "tuner_early_stopping": 5, "tuner_num_trials": 50, "model_info_path": null, "mp_size": 1, "max_train_batch_size": null, "min_train_batch_size": 1, "max_train_micro_batch_size_per_gpu": 1.024000e+03, "min_train_micro_batch_size_per_gpu": 1, "num_tuning_micro_batch_sizes": 3 } [2024-12-10 08:40:10,495] [INFO] [config.py:1003:print] bfloat16_enabled ............. True [2024-12-10 08:40:10,495] [INFO] [config.py:1003:print] bfloat16_immediate_grad_update False [2024-12-10 08:40:10,495] [INFO] [config.py:1003:print] checkpoint_parallel_write_pipeline False [2024-12-10 08:40:10,495] [INFO] [config.py:1003:print] checkpoint_tag_validation_enabled True [2024-12-10 08:40:10,495] [INFO] [config.py:1003:print] checkpoint_tag_validation_fail False [2024-12-10 08:40:10,495] [INFO] [config.py:1003:print] comms_config ................. [2024-12-10 08:40:10,495] [INFO] [config.py:1003:print] communication_data_type ...... None [2024-12-10 08:40:10,495] [INFO] [config.py:1003:print] compression_config ........... {'weight_quantization': {'shared_parameters': {'enabled': False, 'quantizer_kernel': False, 'schedule_offset': 0, 'quantize_groups': 1, 'quantize_verbose': False, 'quantization_type': 'symmetric', 'quantize_weight_in_forward': False, 'rounding': 'nearest', 'fp16_mixed_quantize': False, 'quantize_change_ratio': 0.001}, 'different_groups': {}}, 'activation_quantization': {'shared_parameters': {'enabled': False, 'quantization_type': 'symmetric', 'range_calibration': 'dynamic', 'schedule_offset': 1000}, 'different_groups': {}}, 'sparse_pruning': {'shared_parameters': {'enabled': False, 'method': 'l1', 'schedule_offset': 1000}, 'different_groups': {}}, 'row_pruning': {'shared_parameters': {'enabled': False, 'method': 'l1', 'schedule_offset': 1000}, 'different_groups': {}}, 'head_pruning': {'shared_parameters': {'enabled': False, 'method': 'topk', 'schedule_offset': 1000}, 'different_groups': {}}, 'channel_pruning': {'shared_parameters': {'enabled': False, 'method': 'l1', 'schedule_offset': 1000}, 'different_groups': {}}, 'layer_reduction': {'enabled': False}} [2024-12-10 08:40:10,495] [INFO] [config.py:1003:print] curriculum_enabled_legacy .... False [2024-12-10 08:40:10,495] [INFO] [config.py:1003:print] curriculum_params_legacy ..... False [2024-12-10 08:40:10,495] [INFO] [config.py:1003:print] data_efficiency_config ....... {'enabled': False, 'seed': 1234, 'data_sampling': {'enabled': False, 'num_epochs': 1000, 'num_workers': 0, 'curriculum_learning': {'enabled': False}}, 'data_routing': {'enabled': False, 'random_ltd': {'enabled': False, 'layer_token_lr_schedule': {'enabled': False}}}} [2024-12-10 08:40:10,495] [INFO] [config.py:1003:print] data_efficiency_enabled ...... False [2024-12-10 08:40:10,495] [INFO] [config.py:1003:print] dataloader_drop_last ......... False [2024-12-10 08:40:10,495] [INFO] [config.py:1003:print] disable_allgather ............ False [2024-12-10 08:40:10,495] [INFO] [config.py:1003:print] dump_state ................... False [2024-12-10 08:40:10,495] [INFO] [config.py:1003:print] dynamic_loss_scale_args ...... None [2024-12-10 08:40:10,495] [INFO] [config.py:1003:print] eigenvalue_enabled ........... False [2024-12-10 08:40:10,495] [INFO] [config.py:1003:print] eigenvalue_gas_boundary_resolution 1 [2024-12-10 08:40:10,495] [INFO] [config.py:1003:print] eigenvalue_layer_name ........ bert.encoder.layer [2024-12-10 08:40:10,495] [INFO] [config.py:1003:print] eigenvalue_layer_num ......... 0 [2024-12-10 08:40:10,495] [INFO] [config.py:1003:print] eigenvalue_max_iter .......... 100 [2024-12-10 08:40:10,495] [INFO] [config.py:1003:print] eigenvalue_stability ......... 1e-06 [2024-12-10 08:40:10,495] [INFO] [config.py:1003:print] eigenvalue_tol ............... 0.01 [2024-12-10 08:40:10,495] [INFO] [config.py:1003:print] eigenvalue_verbose ........... False [2024-12-10 08:40:10,495] [INFO] [config.py:1003:print] elasticity_enabled ........... False [2024-12-10 08:40:10,495] [INFO] [config.py:1003:print] flops_profiler_config ........ { "enabled": false, "recompute_fwd_factor": 0.0, "profile_step": 1, "module_depth": -1, "top_modules": 1, "detailed": true, "output_file": null } [2024-12-10 08:40:10,495] [INFO] [config.py:1003:print] fp16_auto_cast ............... None [2024-12-10 08:40:10,495] [INFO] [config.py:1003:print] fp16_enabled ................. False [2024-12-10 08:40:10,495] [INFO] [config.py:1003:print] fp16_master_weights_and_gradients False [2024-12-10 08:40:10,495] [INFO] [config.py:1003:print] global_rank .................. 0 [2024-12-10 08:40:10,495] [INFO] [config.py:1003:print] grad_accum_dtype ............. None [2024-12-10 08:40:10,495] [INFO] [config.py:1003:print] gradient_accumulation_steps .. 1 [2024-12-10 08:40:10,495] [INFO] [config.py:1003:print] gradient_clipping ............ 5.0 [2024-12-10 08:40:10,495] [INFO] [config.py:1003:print] gradient_predivide_factor .... 1.0 [2024-12-10 08:40:10,495] [INFO] [config.py:1003:print] graph_harvesting ............. False [2024-12-10 08:40:10,495] [INFO] [config.py:1003:print] hybrid_engine ................ enabled=False max_out_tokens=512 inference_tp_size=1 release_inference_cache=False pin_parameters=True tp_gather_partition_size=8 [2024-12-10 08:40:10,495] [INFO] [config.py:1003:print] initial_dynamic_scale ........ 1 [2024-12-10 08:40:10,495] [INFO] [config.py:1003:print] load_universal_checkpoint .... False [2024-12-10 08:40:10,495] [INFO] [config.py:1003:print] loss_scale ................... 1.0 [2024-12-10 08:40:10,495] [INFO] [config.py:1003:print] memory_breakdown ............. False [2024-12-10 08:40:10,495] [INFO] [config.py:1003:print] mics_hierarchial_params_gather False [2024-12-10 08:40:10,495] [INFO] [config.py:1003:print] mics_shard_size .............. -1 [2024-12-10 08:40:10,495] [INFO] [config.py:1003:print] monitor_config ............... tensorboard=TensorBoardConfig(enabled=False, output_path='', job_name='DeepSpeedJobName') comet=CometConfig(enabled=False, samples_log_interval=100, project=None, workspace=None, api_key=None, experiment_name=None, experiment_key=None, online=None, mode=None) wandb=WandbConfig(enabled=False, group=None, team=None, project='deepspeed') csv_monitor=CSVConfig(enabled=False, output_path='', job_name='DeepSpeedJobName') [2024-12-10 08:40:10,495] [INFO] [config.py:1003:print] nebula_config ................ { "enabled": false, "persistent_storage_path": null, "persistent_time_interval": 100, "num_of_version_in_retention": 2, "enable_nebula_load": true, "load_path": null } [2024-12-10 08:40:10,495] [INFO] [config.py:1003:print] optimizer_legacy_fusion ...... False [2024-12-10 08:40:10,495] [INFO] [config.py:1003:print] optimizer_name ............... adam [2024-12-10 08:40:10,495] [INFO] [config.py:1003:print] optimizer_params ............. {'lr': 0.0002, 'betas': [0.9, 0.98], 'eps': 1e-06, 'weight_decay': 0.0} [2024-12-10 08:40:10,495] [INFO] [config.py:1003:print] pipeline ..................... {'stages': 'auto', 'partition': 'best', 'seed_layers': False, 'activation_checkpoint_interval': 0, 'pipe_partitioned': True, 'grad_partitioned': True} [2024-12-10 08:40:10,495] [INFO] [config.py:1003:print] pld_enabled .................. False [2024-12-10 08:40:10,496] [INFO] [config.py:1003:print] pld_params ................... False [2024-12-10 08:40:10,496] [INFO] [config.py:1003:print] prescale_gradients ........... False [2024-12-10 08:40:10,496] [INFO] [config.py:1003:print] scheduler_name ............... None [2024-12-10 08:40:10,496] [INFO] [config.py:1003:print] scheduler_params ............. None [2024-12-10 08:40:10,496] [INFO] [config.py:1003:print] seq_parallel_communication_data_type torch.float32 [2024-12-10 08:40:10,496] [INFO] [config.py:1003:print] sparse_attention ............. None [2024-12-10 08:40:10,496] [INFO] [config.py:1003:print] sparse_gradients_enabled ..... False [2024-12-10 08:40:10,496] [INFO] [config.py:1003:print] steps_per_print .............. 1000 [2024-12-10 08:40:10,496] [INFO] [config.py:1003:print] timers_config ................ enabled=True synchronized=True [2024-12-10 08:40:10,496] [INFO] [config.py:1003:print] train_batch_size ............. 16 [2024-12-10 08:40:10,496] [INFO] [config.py:1003:print] train_micro_batch_size_per_gpu 1 [2024-12-10 08:40:10,496] [INFO] [config.py:1003:print] use_data_before_expert_parallel_ False [2024-12-10 08:40:10,496] [INFO] [config.py:1003:print] use_node_local_storage ....... False [2024-12-10 08:40:10,496] [INFO] [config.py:1003:print] wall_clock_breakdown ......... False [2024-12-10 08:40:10,496] [INFO] [config.py:1003:print] weight_quantization_config ... None [2024-12-10 08:40:10,496] [INFO] [config.py:1003:print] world_size ................... 16 [2024-12-10 08:40:10,496] [INFO] [config.py:1003:print] zero_allow_untested_optimizer False [2024-12-10 08:40:10,496] [INFO] [config.py:1003:print] zero_config .................. stage=2 contiguous_gradients=True reduce_scatter=True reduce_bucket_size=500000000 use_multi_rank_bucket_allreduce=True allgather_partitions=True allgather_bucket_size=500000000 overlap_comm=True load_from_fp32_weights=True elastic_checkpoint=False offload_param=None offload_optimizer=None sub_group_size=1000000000 cpu_offload_param=None cpu_offload_use_pin_memory=None cpu_offload=None prefetch_bucket_size=50000000 param_persistence_threshold=100000 model_persistence_threshold=9223372036854775807 max_live_parameters=1000000000 max_reuse_distance=1000000000 gather_16bit_weights_on_model_save=False use_all_reduce_for_fetch_params=False stage3_gather_fp16_weights_on_model_save=False ignore_unused_parameters=True legacy_stage1=False round_robin_gradients=False zero_hpz_partition_size=1 zero_quantized_weights=False zero_quantized_nontrainable_weights=False zero_quantized_gradients=False mics_shard_size=-1 mics_hierarchical_params_gather=False memory_efficient_linear=True pipeline_loading_checkpoint=False override_module_apply=True [2024-12-10 08:40:10,496] [INFO] [config.py:1003:print] zero_enabled ................. True [2024-12-10 08:40:10,496] [INFO] [config.py:1003:print] zero_force_ds_cpu_optimizer .. True [2024-12-10 08:40:10,496] [INFO] [config.py:1003:print] zero_optimization_stage ...... 2 [2024-12-10 08:40:10,496] [INFO] [config.py:989:print_user_config] json = { "train_micro_batch_size_per_gpu": 1, "gradient_accumulation_steps": 1, "gradient_clipping": 5.0, "bf16": { "enabled": true }, "zero_optimization": { "stage": 2, "contiguous_gradients": true, "overlap_comm": true, "reduce_scatter": true, "reduce_bucket_size": 5.000000e+08, "allgather_bucket_size": 5.000000e+08 }, "optimizer": { "type": "Adam", "params": { "lr": 0.0002, "betas": [0.9, 0.98], "eps": 1e-06, "weight_decay": 0.0 } }, "wall_clock_breakdown": false, "steps_per_print": 1000 } [cnode7-008:0/16] 2024-12-10 08:40:10,498 (deepspeed_trainer:75) INFO: Resume training from exp_owsm/s2t_train_05b_ds_raw_bpe50000/checkpoint_40 [2024-12-10 08:40:10,500] [INFO] [torch_checkpoint_engine.py:27:load] [Torch] Loading checkpoint from exp_owsm/s2t_train_05b_ds_raw_bpe50000/checkpoint_40/40/mp_rank_00_model_states.pt... /mnt/home/williamchen/espnet/tools/miniconda/envs/espnet/lib/python3.10/site-packages/deepspeed/runtime/checkpoint_engine/torch_checkpoint_engine.py:28: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature. partition = torch.load(path, map_location=map_location) [2024-12-10 08:40:10,699] [INFO] [torch_checkpoint_engine.py:29:load] [Torch] Loaded checkpoint from exp_owsm/s2t_train_05b_ds_raw_bpe50000/checkpoint_40/40/mp_rank_00_model_states.pt. [2024-12-10 08:40:10,699] [INFO] [torch_checkpoint_engine.py:29:load] [Torch] Loaded checkpoint from exp_owsm/s2t_train_05b_ds_raw_bpe50000/checkpoint_40/40/mp_rank_00_model_states.pt. [2024-12-10 08:40:10,699] [INFO] [torch_checkpoint_engine.py:29:load] [Torch] Loaded checkpoint from exp_owsm/s2t_train_05b_ds_raw_bpe50000/checkpoint_40/40/mp_rank_00_model_states.pt. [2024-12-10 08:40:10,699] [INFO] [torch_checkpoint_engine.py:29:load] [Torch] Loaded checkpoint from exp_owsm/s2t_train_05b_ds_raw_bpe50000/checkpoint_40/40/mp_rank_00_model_states.pt. [2024-12-10 08:40:10,699] [INFO] [torch_checkpoint_engine.py:29:load] [Torch] Loaded checkpoint from exp_owsm/s2t_train_05b_ds_raw_bpe50000/checkpoint_40/40/mp_rank_00_model_states.pt. [2024-12-10 08:40:10,699] [INFO] [torch_checkpoint_engine.py:29:load] [Torch] Loaded checkpoint from exp_owsm/s2t_train_05b_ds_raw_bpe50000/checkpoint_40/40/mp_rank_00_model_states.pt. [2024-12-10 08:40:10,699] [INFO] [torch_checkpoint_engine.py:29:load] [Torch] Loaded checkpoint from exp_owsm/s2t_train_05b_ds_raw_bpe50000/checkpoint_40/40/mp_rank_00_model_states.pt. [2024-12-10 08:40:10,699] [INFO] [torch_checkpoint_engine.py:29:load] [Torch] Loaded checkpoint from exp_owsm/s2t_train_05b_ds_raw_bpe50000/checkpoint_40/40/mp_rank_00_model_states.pt. [2024-12-10 08:40:10,732] [INFO] [torch_checkpoint_engine.py:27:load] [Torch] Loading checkpoint from exp_owsm/s2t_train_05b_ds_raw_bpe50000/checkpoint_40/40/mp_rank_00_model_states.pt... [2024-12-10 08:40:10,783] [INFO] [torch_checkpoint_engine.py:27:load] [Torch] Loading checkpoint from exp_owsm/s2t_train_05b_ds_raw_bpe50000/checkpoint_40/40/mp_rank_00_model_states.pt... [2024-12-10 08:40:10,785] [INFO] [torch_checkpoint_engine.py:27:load] [Torch] Loading checkpoint from exp_owsm/s2t_train_05b_ds_raw_bpe50000/checkpoint_40/40/mp_rank_00_model_states.pt... [2024-12-10 08:40:10,785] [INFO] [torch_checkpoint_engine.py:27:load] [Torch] Loading checkpoint from exp_owsm/s2t_train_05b_ds_raw_bpe50000/checkpoint_40/40/mp_rank_00_model_states.pt... [2024-12-10 08:40:10,786] [INFO] [torch_checkpoint_engine.py:27:load] [Torch] Loading checkpoint from exp_owsm/s2t_train_05b_ds_raw_bpe50000/checkpoint_40/40/mp_rank_00_model_states.pt... [2024-12-10 08:40:10,787] [INFO] [torch_checkpoint_engine.py:27:load] [Torch] Loading checkpoint from exp_owsm/s2t_train_05b_ds_raw_bpe50000/checkpoint_40/40/mp_rank_00_model_states.pt... [2024-12-10 08:40:10,787] [INFO] [torch_checkpoint_engine.py:27:load] [Torch] Loading checkpoint from exp_owsm/s2t_train_05b_ds_raw_bpe50000/checkpoint_40/40/mp_rank_00_model_states.pt... [2024-12-10 08:40:10,788] [INFO] [torch_checkpoint_engine.py:27:load] [Torch] Loading checkpoint from exp_owsm/s2t_train_05b_ds_raw_bpe50000/checkpoint_40/40/mp_rank_00_model_states.pt... [2024-12-10 08:40:11,111] [INFO] [torch_checkpoint_engine.py:29:load] [Torch] Loaded checkpoint from exp_owsm/s2t_train_05b_ds_raw_bpe50000/checkpoint_40/40/mp_rank_00_model_states.pt. [2024-12-10 08:40:11,111] [INFO] [torch_checkpoint_engine.py:29:load] [Torch] Loaded checkpoint from exp_owsm/s2t_train_05b_ds_raw_bpe50000/checkpoint_40/40/mp_rank_00_model_states.pt. [2024-12-10 08:40:11,111] [INFO] [torch_checkpoint_engine.py:29:load] [Torch] Loaded checkpoint from exp_owsm/s2t_train_05b_ds_raw_bpe50000/checkpoint_40/40/mp_rank_00_model_states.pt. [2024-12-10 08:40:11,111] [INFO] [torch_checkpoint_engine.py:29:load] [Torch] Loaded checkpoint from exp_owsm/s2t_train_05b_ds_raw_bpe50000/checkpoint_40/40/mp_rank_00_model_states.pt. [2024-12-10 08:40:11,111] [INFO] [torch_checkpoint_engine.py:29:load] [Torch] Loaded checkpoint from exp_owsm/s2t_train_05b_ds_raw_bpe50000/checkpoint_40/40/mp_rank_00_model_states.pt. [2024-12-10 08:40:11,112] [INFO] [torch_checkpoint_engine.py:29:load] [Torch] Loaded checkpoint from exp_owsm/s2t_train_05b_ds_raw_bpe50000/checkpoint_40/40/mp_rank_00_model_states.pt. [2024-12-10 08:40:11,112] [INFO] [torch_checkpoint_engine.py:29:load] [Torch] Loaded checkpoint from exp_owsm/s2t_train_05b_ds_raw_bpe50000/checkpoint_40/40/mp_rank_00_model_states.pt. [2024-12-10 08:40:11,156] [INFO] [torch_checkpoint_engine.py:27:load] [Torch] Loading checkpoint from exp_owsm/s2t_train_05b_ds_raw_bpe50000/checkpoint_40/40/mp_rank_00_model_states.pt... [2024-12-10 08:40:11,156] [INFO] [torch_checkpoint_engine.py:27:load] [Torch] Loading checkpoint from exp_owsm/s2t_train_05b_ds_raw_bpe50000/checkpoint_40/40/mp_rank_00_model_states.pt... [2024-12-10 08:40:11,164] [INFO] [torch_checkpoint_engine.py:29:load] [Torch] Loaded checkpoint from exp_owsm/s2t_train_05b_ds_raw_bpe50000/checkpoint_40/40/mp_rank_00_model_states.pt. [2024-12-10 08:40:11,176] [INFO] [torch_checkpoint_engine.py:27:load] [Torch] Loading checkpoint from exp_owsm/s2t_train_05b_ds_raw_bpe50000/checkpoint_40/40/mp_rank_00_model_states.pt... [2024-12-10 08:40:11,178] [INFO] [torch_checkpoint_engine.py:27:load] [Torch] Loading checkpoint from exp_owsm/s2t_train_05b_ds_raw_bpe50000/checkpoint_40/40/mp_rank_00_model_states.pt... [2024-12-10 08:40:11,178] [INFO] [torch_checkpoint_engine.py:27:load] [Torch] Loading checkpoint from exp_owsm/s2t_train_05b_ds_raw_bpe50000/checkpoint_40/40/mp_rank_00_model_states.pt... [2024-12-10 08:40:11,179] [INFO] [torch_checkpoint_engine.py:27:load] [Torch] Loading checkpoint from exp_owsm/s2t_train_05b_ds_raw_bpe50000/checkpoint_40/40/mp_rank_00_model_states.pt... [2024-12-10 08:40:11,179] [INFO] [torch_checkpoint_engine.py:27:load] [Torch] Loading checkpoint from exp_owsm/s2t_train_05b_ds_raw_bpe50000/checkpoint_40/40/mp_rank_00_model_states.pt... [2024-12-10 08:40:11,197] [INFO] [torch_checkpoint_engine.py:27:load] [Torch] Loading checkpoint from exp_owsm/s2t_train_05b_ds_raw_bpe50000/checkpoint_40/40/mp_rank_00_model_states.pt... [2024-12-10 08:40:11,394] [INFO] [torch_checkpoint_engine.py:29:load] [Torch] Loaded checkpoint from exp_owsm/s2t_train_05b_ds_raw_bpe50000/checkpoint_40/40/mp_rank_00_model_states.pt. [2024-12-10 08:40:11,411] [INFO] [torch_checkpoint_engine.py:29:load] [Torch] Loaded checkpoint from exp_owsm/s2t_train_05b_ds_raw_bpe50000/checkpoint_40/40/mp_rank_00_model_states.pt. [2024-12-10 08:40:11,412] [INFO] [torch_checkpoint_engine.py:29:load] [Torch] Loaded checkpoint from exp_owsm/s2t_train_05b_ds_raw_bpe50000/checkpoint_40/40/mp_rank_00_model_states.pt. [2024-12-10 08:40:11,412] [INFO] [torch_checkpoint_engine.py:29:load] [Torch] Loaded checkpoint from exp_owsm/s2t_train_05b_ds_raw_bpe50000/checkpoint_40/40/mp_rank_00_model_states.pt. [2024-12-10 08:40:11,412] [INFO] [torch_checkpoint_engine.py:29:load] [Torch] Loaded checkpoint from exp_owsm/s2t_train_05b_ds_raw_bpe50000/checkpoint_40/40/mp_rank_00_model_states.pt. [2024-12-10 08:40:11,412] [INFO] [torch_checkpoint_engine.py:29:load] [Torch] Loaded checkpoint from exp_owsm/s2t_train_05b_ds_raw_bpe50000/checkpoint_40/40/mp_rank_00_model_states.pt. [2024-12-10 08:40:11,412] [INFO] [torch_checkpoint_engine.py:29:load] [Torch] Loaded checkpoint from exp_owsm/s2t_train_05b_ds_raw_bpe50000/checkpoint_40/40/mp_rank_00_model_states.pt. [2024-12-10 08:40:11,415] [INFO] [torch_checkpoint_engine.py:29:load] [Torch] Loaded checkpoint from exp_owsm/s2t_train_05b_ds_raw_bpe50000/checkpoint_40/40/mp_rank_00_model_states.pt. [2024-12-10 08:40:11,776] [INFO] [torch_checkpoint_engine.py:29:load] [Torch] Loaded checkpoint from exp_owsm/s2t_train_05b_ds_raw_bpe50000/checkpoint_40/40/mp_rank_00_model_states.pt. [2024-12-10 08:40:11,778] [INFO] [torch_checkpoint_engine.py:29:load] [Torch] Loaded checkpoint from exp_owsm/s2t_train_05b_ds_raw_bpe50000/checkpoint_40/40/mp_rank_00_model_states.pt. [2024-12-10 08:40:11,824] [INFO] [torch_checkpoint_engine.py:29:load] [Torch] Loaded checkpoint from exp_owsm/s2t_train_05b_ds_raw_bpe50000/checkpoint_40/40/mp_rank_00_model_states.pt. [2024-12-10 08:40:11,825] [INFO] [torch_checkpoint_engine.py:29:load] [Torch] Loaded checkpoint from exp_owsm/s2t_train_05b_ds_raw_bpe50000/checkpoint_40/40/mp_rank_00_model_states.pt. [2024-12-10 08:40:11,825] [INFO] [torch_checkpoint_engine.py:29:load] [Torch] Loaded checkpoint from exp_owsm/s2t_train_05b_ds_raw_bpe50000/checkpoint_40/40/mp_rank_00_model_states.pt. [2024-12-10 08:40:11,826] [INFO] [torch_checkpoint_engine.py:29:load] [Torch] Loaded checkpoint from exp_owsm/s2t_train_05b_ds_raw_bpe50000/checkpoint_40/40/mp_rank_00_model_states.pt. [2024-12-10 08:40:11,826] [INFO] [torch_checkpoint_engine.py:29:load] [Torch] Loaded checkpoint from exp_owsm/s2t_train_05b_ds_raw_bpe50000/checkpoint_40/40/mp_rank_00_model_states.pt. [2024-12-10 08:40:11,826] [INFO] [torch_checkpoint_engine.py:29:load] [Torch] Loaded checkpoint from exp_owsm/s2t_train_05b_ds_raw_bpe50000/checkpoint_40/40/mp_rank_00_model_states.pt. [2024-12-10 08:40:11,602] [INFO] [torch_checkpoint_engine.py:27:load] [Torch] Loading checkpoint from exp_owsm/s2t_train_05b_ds_raw_bpe50000/checkpoint_40/40/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt... [2024-12-10 08:40:11,652] [INFO] [torch_checkpoint_engine.py:27:load] [Torch] Loading checkpoint from exp_owsm/s2t_train_05b_ds_raw_bpe50000/checkpoint_40/40/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt... [2024-12-10 08:40:11,654] [INFO] [torch_checkpoint_engine.py:27:load] [Torch] Loading checkpoint from exp_owsm/s2t_train_05b_ds_raw_bpe50000/checkpoint_40/40/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt... [2024-12-10 08:40:11,655] [INFO] [torch_checkpoint_engine.py:27:load] [Torch] Loading checkpoint from exp_owsm/s2t_train_05b_ds_raw_bpe50000/checkpoint_40/40/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt... [2024-12-10 08:40:11,660] [INFO] [torch_checkpoint_engine.py:27:load] [Torch] Loading checkpoint from exp_owsm/s2t_train_05b_ds_raw_bpe50000/checkpoint_40/40/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt... [2024-12-10 08:40:12,005] [INFO] [torch_checkpoint_engine.py:27:load] [Torch] Loading checkpoint from exp_owsm/s2t_train_05b_ds_raw_bpe50000/checkpoint_40/40/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt... [2024-12-10 08:40:11,694] [INFO] [torch_checkpoint_engine.py:27:load] [Torch] Loading checkpoint from exp_owsm/s2t_train_05b_ds_raw_bpe50000/checkpoint_40/40/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt... [2024-12-10 08:40:11,694] [INFO] [torch_checkpoint_engine.py:27:load] [Torch] Loading checkpoint from exp_owsm/s2t_train_05b_ds_raw_bpe50000/checkpoint_40/40/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt... [2024-12-10 08:40:11,699] [INFO] [torch_checkpoint_engine.py:27:load] [Torch] Loading checkpoint from exp_owsm/s2t_train_05b_ds_raw_bpe50000/checkpoint_40/40/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt... [2024-12-10 08:40:12,020] [INFO] [torch_checkpoint_engine.py:27:load] [Torch] Loading checkpoint from exp_owsm/s2t_train_05b_ds_raw_bpe50000/checkpoint_40/40/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt... [2024-12-10 08:40:12,044] [INFO] [torch_checkpoint_engine.py:27:load] [Torch] Loading checkpoint from exp_owsm/s2t_train_05b_ds_raw_bpe50000/checkpoint_40/40/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt... [2024-12-10 08:40:12,060] [INFO] [torch_checkpoint_engine.py:27:load] [Torch] Loading checkpoint from exp_owsm/s2t_train_05b_ds_raw_bpe50000/checkpoint_40/40/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt... [2024-12-10 08:40:12,062] [INFO] [torch_checkpoint_engine.py:27:load] [Torch] Loading checkpoint from exp_owsm/s2t_train_05b_ds_raw_bpe50000/checkpoint_40/40/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt... [2024-12-10 08:40:12,065] [INFO] [torch_checkpoint_engine.py:27:load] [Torch] Loading checkpoint from exp_owsm/s2t_train_05b_ds_raw_bpe50000/checkpoint_40/40/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt... [2024-12-10 08:40:12,067] [INFO] [torch_checkpoint_engine.py:27:load] [Torch] Loading checkpoint from exp_owsm/s2t_train_05b_ds_raw_bpe50000/checkpoint_40/40/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt... [2024-12-10 08:40:12,096] [INFO] [torch_checkpoint_engine.py:27:load] [Torch] Loading checkpoint from exp_owsm/s2t_train_05b_ds_raw_bpe50000/checkpoint_40/40/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt... [2024-12-10 08:40:12,428] [INFO] [torch_checkpoint_engine.py:29:load] [Torch] Loaded checkpoint from exp_owsm/s2t_train_05b_ds_raw_bpe50000/checkpoint_40/40/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt. [2024-12-10 08:40:12,428] [INFO] [torch_checkpoint_engine.py:29:load] [Torch] Loaded checkpoint from exp_owsm/s2t_train_05b_ds_raw_bpe50000/checkpoint_40/40/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt. [2024-12-10 08:40:12,429] [INFO] [engine.py:3076:_get_all_zero_checkpoint_state_dicts] successfully read 16 ZeRO state_dicts for rank 6 [2024-12-10 08:40:12,429] [INFO] [engine.py:3076:_get_all_zero_checkpoint_state_dicts] successfully read 16 ZeRO state_dicts for rank 1 [2024-12-10 08:40:12,487] [INFO] [engine.py:3026:_load_zero_checkpoint] loading 16 zero partition checkpoints for rank 1 [2024-12-10 08:40:12,496] [INFO] [engine.py:3026:_load_zero_checkpoint] loading 16 zero partition checkpoints for rank 6 [2024-12-10 08:40:12,188] [INFO] [torch_checkpoint_engine.py:29:load] [Torch] Loaded checkpoint from exp_owsm/s2t_train_05b_ds_raw_bpe50000/checkpoint_40/40/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt. [2024-12-10 08:40:12,189] [INFO] [engine.py:3076:_get_all_zero_checkpoint_state_dicts] successfully read 16 ZeRO state_dicts for rank 12 [2024-12-10 08:40:12,548] [INFO] [torch_checkpoint_engine.py:29:load] [Torch] Loaded checkpoint from exp_owsm/s2t_train_05b_ds_raw_bpe50000/checkpoint_40/40/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt. [2024-12-10 08:40:12,548] [INFO] [engine.py:3076:_get_all_zero_checkpoint_state_dicts] successfully read 16 ZeRO state_dicts for rank 7 [2024-12-10 08:40:12,232] [INFO] [torch_checkpoint_engine.py:29:load] [Torch] Loaded checkpoint from exp_owsm/s2t_train_05b_ds_raw_bpe50000/checkpoint_40/40/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt. [2024-12-10 08:40:12,232] [INFO] [engine.py:3076:_get_all_zero_checkpoint_state_dicts] successfully read 16 ZeRO state_dicts for rank 15 [2024-12-10 08:40:12,253] [INFO] [torch_checkpoint_engine.py:29:load] [Torch] Loaded checkpoint from exp_owsm/s2t_train_05b_ds_raw_bpe50000/checkpoint_40/40/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt. [2024-12-10 08:40:12,253] [INFO] [engine.py:3076:_get_all_zero_checkpoint_state_dicts] successfully read 16 ZeRO state_dicts for rank 11 [2024-12-10 08:40:12,256] [INFO] [engine.py:3026:_load_zero_checkpoint] loading 16 zero partition checkpoints for rank 12 [2024-12-10 08:40:12,267] [INFO] [torch_checkpoint_engine.py:29:load] [Torch] Loaded checkpoint from exp_owsm/s2t_train_05b_ds_raw_bpe50000/checkpoint_40/40/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt. [2024-12-10 08:40:12,268] [INFO] [engine.py:3076:_get_all_zero_checkpoint_state_dicts] successfully read 16 ZeRO state_dicts for rank 10 [2024-12-10 08:40:12,608] [INFO] [torch_checkpoint_engine.py:29:load] [Torch] Loaded checkpoint from exp_owsm/s2t_train_05b_ds_raw_bpe50000/checkpoint_40/40/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt. [2024-12-10 08:40:12,608] [INFO] [engine.py:3076:_get_all_zero_checkpoint_state_dicts] successfully read 16 ZeRO state_dicts for rank 4 [2024-12-10 08:40:12,610] [INFO] [engine.py:3026:_load_zero_checkpoint] loading 16 zero partition checkpoints for rank 7 [2024-12-10 08:40:12,299] [INFO] [torch_checkpoint_engine.py:29:load] [Torch] Loaded checkpoint from exp_owsm/s2t_train_05b_ds_raw_bpe50000/checkpoint_40/40/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt. [2024-12-10 08:40:12,299] [INFO] [engine.py:3076:_get_all_zero_checkpoint_state_dicts] successfully read 16 ZeRO state_dicts for rank 8 [2024-12-10 08:40:12,312] [INFO] [engine.py:3026:_load_zero_checkpoint] loading 16 zero partition checkpoints for rank 11 [2024-12-10 08:40:12,324] [INFO] [engine.py:3026:_load_zero_checkpoint] loading 16 zero partition checkpoints for rank 10 [2024-12-10 08:40:12,652] [INFO] [torch_checkpoint_engine.py:29:load] [Torch] Loaded checkpoint from exp_owsm/s2t_train_05b_ds_raw_bpe50000/checkpoint_40/40/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt. [2024-12-10 08:40:12,653] [INFO] [engine.py:3076:_get_all_zero_checkpoint_state_dicts] successfully read 16 ZeRO state_dicts for rank 5 [2024-12-10 08:40:12,656] [INFO] [torch_checkpoint_engine.py:29:load] [Torch] Loaded checkpoint from exp_owsm/s2t_train_05b_ds_raw_bpe50000/checkpoint_40/40/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt. [2024-12-10 08:40:12,656] [INFO] [engine.py:3076:_get_all_zero_checkpoint_state_dicts] successfully read 16 ZeRO state_dicts for rank 0 [2024-12-10 08:40:12,671] [INFO] [engine.py:3026:_load_zero_checkpoint] loading 16 zero partition checkpoints for rank 4 [2024-12-10 08:40:12,385] [INFO] [engine.py:3026:_load_zero_checkpoint] loading 16 zero partition checkpoints for rank 15 [2024-12-10 08:40:12,710] [INFO] [engine.py:3026:_load_zero_checkpoint] loading 16 zero partition checkpoints for rank 0 [2024-12-10 08:40:12,710] [INFO] [engine.py:3026:_load_zero_checkpoint] loading 16 zero partition checkpoints for rank 5 [2024-12-10 08:40:12,720] [INFO] [torch_checkpoint_engine.py:29:load] [Torch] Loaded checkpoint from exp_owsm/s2t_train_05b_ds_raw_bpe50000/checkpoint_40/40/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt. [2024-12-10 08:40:12,720] [INFO] [engine.py:3076:_get_all_zero_checkpoint_state_dicts] successfully read 16 ZeRO state_dicts for rank 3 [cnode7-008:0/16] 2024-12-10 08:40:12,725 (multiple_iter_factory:32) INFO: Building 0th iter-factory... [2024-12-10 08:40:12,412] [INFO] [engine.py:3026:_load_zero_checkpoint] loading 16 zero partition checkpoints for rank 8 [2024-12-10 08:40:12,786] [INFO] [torch_checkpoint_engine.py:29:load] [Torch] Loaded checkpoint from exp_owsm/s2t_train_05b_ds_raw_bpe50000/checkpoint_40/40/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt. [2024-12-10 08:40:12,787] [INFO] [engine.py:3076:_get_all_zero_checkpoint_state_dicts] successfully read 16 ZeRO state_dicts for rank 2 [2024-12-10 08:40:12,467] [INFO] [torch_checkpoint_engine.py:29:load] [Torch] Loaded checkpoint from exp_owsm/s2t_train_05b_ds_raw_bpe50000/checkpoint_40/40/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt. [2024-12-10 08:40:12,467] [INFO] [engine.py:3076:_get_all_zero_checkpoint_state_dicts] successfully read 16 ZeRO state_dicts for rank 13 [2024-12-10 08:40:12,814] [INFO] [engine.py:3026:_load_zero_checkpoint] loading 16 zero partition checkpoints for rank 3 [2024-12-10 08:40:12,502] [INFO] [torch_checkpoint_engine.py:29:load] [Torch] Loaded checkpoint from exp_owsm/s2t_train_05b_ds_raw_bpe50000/checkpoint_40/40/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt. [2024-12-10 08:40:12,503] [INFO] [engine.py:3076:_get_all_zero_checkpoint_state_dicts] successfully read 16 ZeRO state_dicts for rank 9 [2024-12-10 08:40:12,531] [INFO] [torch_checkpoint_engine.py:29:load] [Torch] Loaded checkpoint from exp_owsm/s2t_train_05b_ds_raw_bpe50000/checkpoint_40/40/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt. [2024-12-10 08:40:12,531] [INFO] [engine.py:3076:_get_all_zero_checkpoint_state_dicts] successfully read 16 ZeRO state_dicts for rank 14 [2024-12-10 08:40:12,863] [INFO] [engine.py:3026:_load_zero_checkpoint] loading 16 zero partition checkpoints for rank 2 [2024-12-10 08:40:12,561] [INFO] [engine.py:3026:_load_zero_checkpoint] loading 16 zero partition checkpoints for rank 9 [2024-12-10 08:40:12,585] [INFO] [engine.py:3026:_load_zero_checkpoint] loading 16 zero partition checkpoints for rank 13 [2024-12-10 08:40:12,586] [INFO] [engine.py:3026:_load_zero_checkpoint] loading 16 zero partition checkpoints for rank 14 [cnode7-008:0/16] 2024-12-10 08:40:38,951 (s2t:444) INFO: Optional Data Names: ('text_prev', 'text_ctc', 'text_spk2', 'text_spk3', 'text_spk4') [cnode7-008:0/16] 2024-12-10 08:40:55,674 (abs_task:1807) INFO: [train] dataset: ESPnetDataset( speech: {"path": "exp_owsm/s2t_stats_raw_bpe50000/splits8/wav.scp/split.7", "type": "kaldi_ark"} text_prev: {"path": "exp_owsm/s2t_stats_raw_bpe50000/splits8/text.prev/split.7", "type": "text"} text_ctc: {"path": "exp_owsm/s2t_stats_raw_bpe50000/splits8/text.ctc/split.7", "type": "text"} text: {"path": "exp_owsm/s2t_stats_raw_bpe50000/splits8/text/split.7", "type": "text"} preprocess: ) [cnode7-008:0/16] 2024-12-10 08:40:55,674 (abs_task:1808) INFO: [train] Batch sampler: SortedBatchSampler(N-batch=28521, batch_size=256, shape_file=exp_owsm/s2t_stats_raw_bpe50000/splits8/speech_shape/split.7, sort_in_batch=descending, sort_batch=descending) [cnode7-008:0/16] 2024-12-10 08:40:55,677 (abs_task:1809) INFO: [train] mini-batch sizes summary: N-batch=28521, mean=256.0, min=256, max=257 [2024-12-10 08:41:17,066] [INFO] [real_accelerator.py:219:get_accelerator] Setting ds_accelerator to cuda (auto detect) [2024-12-10 08:41:16,778] [INFO] [real_accelerator.py:219:get_accelerator] Setting ds_accelerator to cuda (auto detect) [2024-12-10 08:41:18,863] [INFO] [real_accelerator.py:219:get_accelerator] Setting ds_accelerator to cuda (auto detect) [2024-12-10 08:41:19,961] [INFO] [real_accelerator.py:219:get_accelerator] Setting ds_accelerator to cuda (auto detect) [2024-12-10 08:41:20,363] [INFO] [real_accelerator.py:219:get_accelerator] Setting ds_accelerator to cuda (auto detect) [2024-12-10 08:41:20,871] [INFO] [real_accelerator.py:219:get_accelerator] Setting ds_accelerator to cuda (auto detect) [2024-12-10 08:41:20,951] [INFO] [real_accelerator.py:219:get_accelerator] Setting ds_accelerator to cuda (auto detect) [2024-12-10 08:41:21,004] [INFO] [real_accelerator.py:219:get_accelerator] Setting ds_accelerator to cuda (auto detect) [2024-12-10 08:41:21,051] [INFO] [real_accelerator.py:219:get_accelerator] Setting ds_accelerator to cuda (auto detect) [2024-12-10 08:41:21,500] [INFO] [real_accelerator.py:219:get_accelerator] Setting ds_accelerator to cuda (auto detect) [2024-12-10 08:41:21,501] [INFO] [real_accelerator.py:219:get_accelerator] Setting ds_accelerator to cuda (auto detect) [2024-12-10 08:41:21,605] [INFO] [real_accelerator.py:219:get_accelerator] Setting ds_accelerator to cuda (auto detect) [2024-12-10 08:41:21,650] [INFO] [real_accelerator.py:219:get_accelerator] Setting ds_accelerator to cuda (auto detect) [2024-12-10 08:41:21,700] [INFO] [real_accelerator.py:219:get_accelerator] Setting ds_accelerator to cuda (auto detect) [2024-12-10 08:41:21,961] [INFO] [real_accelerator.py:219:get_accelerator] Setting ds_accelerator to cuda (auto detect) [2024-12-10 08:41:31,611] [INFO] [real_accelerator.py:219:get_accelerator] Setting ds_accelerator to cuda (auto detect) [2024-12-10 08:42:03,641] [INFO] [real_accelerator.py:219:get_accelerator] Setting ds_accelerator to cuda (auto detect) [2024-12-10 08:42:07,827] [INFO] [real_accelerator.py:219:get_accelerator] Setting ds_accelerator to cuda (auto detect) [2024-12-10 08:42:08,406] [INFO] [real_accelerator.py:219:get_accelerator] Setting ds_accelerator to cuda (auto detect) [2024-12-10 08:42:08,924] [INFO] [real_accelerator.py:219:get_accelerator] Setting ds_accelerator to cuda (auto detect) [2024-12-10 08:42:08,683] [INFO] [real_accelerator.py:219:get_accelerator] Setting ds_accelerator to cuda (auto detect) [2024-12-10 08:42:09,235] [INFO] [real_accelerator.py:219:get_accelerator] Setting ds_accelerator to cuda (auto detect) [2024-12-10 08:42:09,610] [INFO] [real_accelerator.py:219:get_accelerator] Setting ds_accelerator to cuda (auto detect) [2024-12-10 08:42:09,899] [INFO] [real_accelerator.py:219:get_accelerator] Setting ds_accelerator to cuda (auto detect) [2024-12-10 08:42:09,636] [INFO] [real_accelerator.py:219:get_accelerator] Setting ds_accelerator to cuda (auto detect) [2024-12-10 08:42:10,138] [INFO] [real_accelerator.py:219:get_accelerator] Setting ds_accelerator to cuda (auto detect) [2024-12-10 08:42:10,699] [INFO] [real_accelerator.py:219:get_accelerator] Setting ds_accelerator to cuda (auto detect) [2024-12-10 08:42:11,345] [INFO] [real_accelerator.py:219:get_accelerator] Setting ds_accelerator to cuda (auto detect) [2024-12-10 08:42:11,398] [INFO] [real_accelerator.py:219:get_accelerator] Setting ds_accelerator to cuda (auto detect) [2024-12-10 08:42:11,675] [INFO] [real_accelerator.py:219:get_accelerator] Setting ds_accelerator to cuda (auto detect) [2024-12-10 08:42:21,089] [INFO] [real_accelerator.py:219:get_accelerator] Setting ds_accelerator to cuda (auto detect) [2024-12-10 08:42:23,797] [INFO] [real_accelerator.py:219:get_accelerator] Setting ds_accelerator to cuda (auto detect) [2024-12-10 08:42:50,235] [INFO] [real_accelerator.py:219:get_accelerator] Setting ds_accelerator to cuda (auto detect) [2024-12-10 08:42:56,633] [INFO] [real_accelerator.py:219:get_accelerator] Setting ds_accelerator to cuda (auto detect) [2024-12-10 08:42:56,816] [INFO] [real_accelerator.py:219:get_accelerator] Setting ds_accelerator to cuda (auto detect) [2024-12-10 08:42:57,402] [INFO] [real_accelerator.py:219:get_accelerator] Setting ds_accelerator to cuda (auto detect) [2024-12-10 08:42:57,489] [INFO] [real_accelerator.py:219:get_accelerator] Setting ds_accelerator to cuda (auto detect) [2024-12-10 08:42:58,084] [INFO] [real_accelerator.py:219:get_accelerator] Setting ds_accelerator to cuda (auto detect) [2024-12-10 08:42:58,518] [INFO] [real_accelerator.py:219:get_accelerator] Setting ds_accelerator to cuda (auto detect) [2024-12-10 08:42:58,857] [INFO] [real_accelerator.py:219:get_accelerator] Setting ds_accelerator to cuda (auto detect) [2024-12-10 08:42:58,807] [INFO] [real_accelerator.py:219:get_accelerator] Setting ds_accelerator to cuda (auto detect) [2024-12-10 08:42:59,736] [INFO] [real_accelerator.py:219:get_accelerator] Setting ds_accelerator to cuda (auto detect) [2024-12-10 08:42:59,992] [INFO] [real_accelerator.py:219:get_accelerator] Setting ds_accelerator to cuda (auto detect) [2024-12-10 08:43:00,842] [INFO] [real_accelerator.py:219:get_accelerator] Setting ds_accelerator to cuda (auto detect) [2024-12-10 08:43:00,898] [INFO] [real_accelerator.py:219:get_accelerator] Setting ds_accelerator to cuda (auto detect) [2024-12-10 08:43:02,466] [INFO] [real_accelerator.py:219:get_accelerator] Setting ds_accelerator to cuda (auto detect) [2024-12-10 08:43:09,425] [INFO] [real_accelerator.py:219:get_accelerator] Setting ds_accelerator to cuda (auto detect) [2024-12-10 08:43:13,300] [INFO] [real_accelerator.py:219:get_accelerator] Setting ds_accelerator to cuda (auto detect) [2024-12-10 08:43:36,430] [INFO] [real_accelerator.py:219:get_accelerator] Setting ds_accelerator to cuda (auto detect) [2024-12-10 08:43:45,726] [INFO] [real_accelerator.py:219:get_accelerator] Setting ds_accelerator to cuda (auto detect) [2024-12-10 08:43:46,224] [INFO] [real_accelerator.py:219:get_accelerator] Setting ds_accelerator to cuda (auto detect) [2024-12-10 08:43:46,231] [INFO] [real_accelerator.py:219:get_accelerator] Setting ds_accelerator to cuda (auto detect) [2024-12-10 08:43:46,327] [INFO] [real_accelerator.py:219:get_accelerator] Setting ds_accelerator to cuda (auto detect) [2024-12-10 08:43:46,898] [INFO] [real_accelerator.py:219:get_accelerator] Setting ds_accelerator to cuda (auto detect) [2024-12-10 08:43:47,473] [INFO] [real_accelerator.py:219:get_accelerator] Setting ds_accelerator to cuda (auto detect) [2024-12-10 08:43:47,762] [INFO] [real_accelerator.py:219:get_accelerator] Setting ds_accelerator to cuda (auto detect) [2024-12-10 08:43:48,762] [INFO] [real_accelerator.py:219:get_accelerator] Setting ds_accelerator to cuda (auto detect) [2024-12-10 08:43:49,194] [INFO] [real_accelerator.py:219:get_accelerator] Setting ds_accelerator to cuda (auto detect) [2024-12-10 08:43:49,758] [INFO] [real_accelerator.py:219:get_accelerator] Setting ds_accelerator to cuda (auto detect) [2024-12-10 08:43:51,252] [INFO] [real_accelerator.py:219:get_accelerator] Setting ds_accelerator to cuda (auto detect) [2024-12-10 08:43:51,370] [INFO] [real_accelerator.py:219:get_accelerator] Setting ds_accelerator to cuda (auto detect) [2024-12-10 08:43:54,659] [INFO] [real_accelerator.py:219:get_accelerator] Setting ds_accelerator to cuda (auto detect) [2024-12-10 08:43:57,691] [INFO] [real_accelerator.py:219:get_accelerator] Setting ds_accelerator to cuda (auto detect) /mnt/home/williamchen/espnet/espnet2/s2t/espnet_model.py:279: FutureWarning: `torch.cuda.amp.autocast(args...)` is deprecated. Please use `torch.amp.autocast('cuda', args...)` instead. with autocast(False): [2024-12-10 08:44:02,373] [INFO] [real_accelerator.py:219:get_accelerator] Setting ds_accelerator to cuda (auto detect) /mnt/home/williamchen/espnet/espnet2/s2t/espnet_model.py:279: FutureWarning: `torch.cuda.amp.autocast(args...)` is deprecated. Please use `torch.amp.autocast('cuda', args...)` instead. with autocast(False): /mnt/home/williamchen/espnet/espnet2/s2t/espnet_model.py:279: FutureWarning: `torch.cuda.amp.autocast(args...)` is deprecated. Please use `torch.amp.autocast('cuda', args...)` instead. with autocast(False): /mnt/home/williamchen/espnet/espnet2/s2t/espnet_model.py:279: FutureWarning: `torch.cuda.amp.autocast(args...)` is deprecated. Please use `torch.amp.autocast('cuda', args...)` instead. with autocast(False): cnode7-008:628123:637496 [0] NCCL INFO Using non-device net plugin version 0 cnode7-008:628123:637496 [0] NCCL INFO Using network IB cnode7-008:628127:637497 [4] NCCL INFO Using non-device net plugin version 0 cnode7-008:628127:637497 [4] NCCL INFO Using network IB cnode7-008:628124:637498 [1] NCCL INFO Using non-device net plugin version 0 cnode7-008:628124:637498 [1] NCCL INFO Using network IB /mnt/home/williamchen/espnet/espnet2/s2t/espnet_model.py:279: FutureWarning: `torch.cuda.amp.autocast(args...)` is deprecated. Please use `torch.amp.autocast('cuda', args...)` instead. with autocast(False): /mnt/home/williamchen/espnet/espnet2/s2t/espnet_model.py:279: FutureWarning: `torch.cuda.amp.autocast(args...)` is deprecated. Please use `torch.amp.autocast('cuda', args...)` instead. with autocast(False): cnode7-008:628129:637512 [6] NCCL INFO Using non-device net plugin version 0 cnode7-008:628129:637512 [6] NCCL INFO Using network IB cnode7-008:628128:637782 [5] NCCL INFO Using non-device net plugin version 0 cnode7-008:628128:637782 [5] NCCL INFO Using network IB /mnt/home/williamchen/espnet/espnet2/s2t/espnet_model.py:279: FutureWarning: `torch.cuda.amp.autocast(args...)` is deprecated. Please use `torch.amp.autocast('cuda', args...)` instead. with autocast(False): cnode7-008:628126:637787 [3] NCCL INFO Using non-device net plugin version 0 cnode7-008:628126:637787 [3] NCCL INFO Using network IB /mnt/home/williamchen/espnet/espnet2/s2t/espnet_model.py:279: FutureWarning: `torch.cuda.amp.autocast(args...)` is deprecated. Please use `torch.amp.autocast('cuda', args...)` instead. with autocast(False): /mnt/home/williamchen/espnet/espnet2/s2t/espnet_model.py:279: FutureWarning: `torch.cuda.amp.autocast(args...)` is deprecated. Please use `torch.amp.autocast('cuda', args...)` instead. with autocast(False): cnode7-008:628125:637915 [2] NCCL INFO Using non-device net plugin version 0 cnode7-008:628125:637915 [2] NCCL INFO Using network IB cnode7-008:628130:637920 [7] NCCL INFO Using non-device net plugin version 0 cnode7-008:628130:637920 [7] NCCL INFO Using network IB /mnt/home/williamchen/espnet/espnet2/s2t/espnet_model.py:279: FutureWarning: `torch.cuda.amp.autocast(args...)` is deprecated. Please use `torch.amp.autocast('cuda', args...)` instead. with autocast(False): /mnt/home/williamchen/espnet/espnet2/s2t/espnet_model.py:279: FutureWarning: `torch.cuda.amp.autocast(args...)` is deprecated. Please use `torch.amp.autocast('cuda', args...)` instead. with autocast(False): cnode7-009:270308:279372 [0] NCCL INFO Using non-device net plugin version 0 cnode7-009:270308:279372 [0] NCCL INFO Using network IB cnode7-009:270310:279373 [2] NCCL INFO Using non-device net plugin version 0 cnode7-009:270310:279373 [2] NCCL INFO Using network IB cnode7-009:270314:279443 [6] NCCL INFO Using non-device net plugin version 0 cnode7-009:270314:279443 [6] NCCL INFO Using network IB /mnt/home/williamchen/espnet/espnet2/s2t/espnet_model.py:279: FutureWarning: `torch.cuda.amp.autocast(args...)` is deprecated. Please use `torch.amp.autocast('cuda', args...)` instead. with autocast(False): /mnt/home/williamchen/espnet/espnet2/s2t/espnet_model.py:279: FutureWarning: `torch.cuda.amp.autocast(args...)` is deprecated. Please use `torch.amp.autocast('cuda', args...)` instead. with autocast(False): cnode7-009:270311:279721 [3] NCCL INFO Using non-device net plugin version 0 cnode7-009:270311:279721 [3] NCCL INFO Using network IB cnode7-009:270313:279722 [5] NCCL INFO Using non-device net plugin version 0 cnode7-009:270313:279722 [5] NCCL INFO Using network IB /mnt/home/williamchen/espnet/espnet2/s2t/espnet_model.py:279: FutureWarning: `torch.cuda.amp.autocast(args...)` is deprecated. Please use `torch.amp.autocast('cuda', args...)` instead. with autocast(False): cnode7-009:270312:279866 [4] NCCL INFO Using non-device net plugin version 0 cnode7-009:270312:279866 [4] NCCL INFO Using network IB /mnt/home/williamchen/espnet/espnet2/s2t/espnet_model.py:279: FutureWarning: `torch.cuda.amp.autocast(args...)` is deprecated. Please use `torch.amp.autocast('cuda', args...)` instead. with autocast(False): cnode7-009:270309:280008 [1] NCCL INFO Using non-device net plugin version 0 cnode7-009:270309:280008 [1] NCCL INFO Using network IB /mnt/home/williamchen/espnet/espnet2/s2t/espnet_model.py:279: FutureWarning: `torch.cuda.amp.autocast(args...)` is deprecated. Please use `torch.amp.autocast('cuda', args...)` instead. with autocast(False): cnode7-008:628123:637496 [0] NCCL INFO comm 0x5555b6f0a570 rank 0 nranks 16 cudaDev 0 nvmlDev 0 busId 1b000 commId 0x34e5a2ca30f589ad - Init START cnode7-008:628127:637497 [4] NCCL INFO comm 0x5555c0f3bf20 rank 4 nranks 16 cudaDev 4 nvmlDev 4 busId 9d000 commId 0x34e5a2ca30f589ad - Init START cnode7-008:628130:637920 [7] NCCL INFO comm 0x5555c0efc560 rank 7 nranks 16 cudaDev 7 nvmlDev 7 busId df000 commId 0x34e5a2ca30f589ad - Init START cnode7-008:628124:637498 [1] NCCL INFO comm 0x5555c0f0dbb0 rank 1 nranks 16 cudaDev 1 nvmlDev 1 busId 43000 commId 0x34e5a2ca30f589ad - Init START cnode7-009:270310:279373 [2] NCCL INFO comm 0x5555c0f31ff0 rank 10 nranks 16 cudaDev 2 nvmlDev 2 busId 52000 commId 0x34e5a2ca30f589ad - Init START cnode7-009:270313:279722 [5] NCCL INFO comm 0x5555c0f35c90 rank 13 nranks 16 cudaDev 5 nvmlDev 5 busId c3000 commId 0x34e5a2ca30f589ad - Init START cnode7-008:628128:637782 [5] NCCL INFO comm 0x5555c0f235b0 rank 5 nranks 16 cudaDev 5 nvmlDev 5 busId c3000 commId 0x34e5a2ca30f589ad - Init START cnode7-008:628129:637512 [6] NCCL INFO comm 0x5555c0eeb970 rank 6 nranks 16 cudaDev 6 nvmlDev 6 busId d1000 commId 0x34e5a2ca30f589ad - Init START cnode7-008:628126:637787 [3] NCCL INFO comm 0x5555be768d90 rank 3 nranks 16 cudaDev 3 nvmlDev 3 busId 61000 commId 0x34e5a2ca30f589ad - Init START cnode7-009:270314:279443 [6] NCCL INFO comm 0x5555c0f38de0 rank 14 nranks 16 cudaDev 6 nvmlDev 6 busId d1000 commId 0x34e5a2ca30f589ad - Init START cnode7-009:270315:280163 [7] NCCL INFO Using non-device net plugin version 0 cnode7-009:270315:280163 [7] NCCL INFO Using network IB cnode7-009:270315:280163 [7] NCCL INFO comm 0x5555c0eedd70 rank 15 nranks 16 cudaDev 7 nvmlDev 7 busId df000 commId 0x34e5a2ca30f589ad - Init START cnode7-009:270308:279372 [0] NCCL INFO comm 0x5555b6f4b630 rank 8 nranks 16 cudaDev 0 nvmlDev 0 busId 1b000 commId 0x34e5a2ca30f589ad - Init START cnode7-009:270311:279721 [3] NCCL INFO comm 0x5555c0f259a0 rank 11 nranks 16 cudaDev 3 nvmlDev 3 busId 61000 commId 0x34e5a2ca30f589ad - Init START cnode7-009:270312:279866 [4] NCCL INFO comm 0x5555c0f25440 rank 12 nranks 16 cudaDev 4 nvmlDev 4 busId 9d000 commId 0x34e5a2ca30f589ad - Init START cnode7-009:270309:280008 [1] NCCL INFO comm 0x5555d4f28520 rank 9 nranks 16 cudaDev 1 nvmlDev 1 busId 43000 commId 0x34e5a2ca30f589ad - Init START cnode7-008:628125:637915 [2] NCCL INFO comm 0x5555c0f2fd80 rank 2 nranks 16 cudaDev 2 nvmlDev 2 busId 52000 commId 0x34e5a2ca30f589ad - Init START cnode7-009:270308:279372 [0] NCCL INFO Setting affinity for GPU 0 to ff,ffffffff,ffff0000,00000000,00ffffff,ffffffff cnode7-009:270308:279372 [0] NCCL INFO NVLS multicast support is available on dev 0 cnode7-009:270310:279373 [2] NCCL INFO Setting affinity for GPU 2 to ff,ffffffff,ffff0000,00000000,00ffffff,ffffffff cnode7-009:270310:279373 [2] NCCL INFO NVLS multicast support is available on dev 2 cnode7-009:270313:279722 [5] NCCL INFO Setting affinity for GPU 5 to ffffffff,ffffff00,00000000,0000ffff,ffffffff,ff000000,00000000 cnode7-009:270313:279722 [5] NCCL INFO NVLS multicast support is available on dev 5 cnode7-009:270314:279443 [6] NCCL INFO Setting affinity for GPU 6 to ffffffff,ffffff00,00000000,0000ffff,ffffffff,ff000000,00000000 cnode7-009:270314:279443 [6] NCCL INFO NVLS multicast support is available on dev 6 cnode7-009:270311:279721 [3] NCCL INFO Setting affinity for GPU 3 to ff,ffffffff,ffff0000,00000000,00ffffff,ffffffff cnode7-009:270311:279721 [3] NCCL INFO NVLS multicast support is available on dev 3 cnode7-009:270312:279866 [4] NCCL INFO Setting affinity for GPU 4 to ffffffff,ffffff00,00000000,0000ffff,ffffffff,ff000000,00000000 cnode7-009:270312:279866 [4] NCCL INFO NVLS multicast support is available on dev 4 cnode7-009:270315:280163 [7] NCCL INFO Setting affinity for GPU 7 to ffffffff,ffffff00,00000000,0000ffff,ffffffff,ff000000,00000000 cnode7-009:270315:280163 [7] NCCL INFO NVLS multicast support is available on dev 7 cnode7-009:270309:280008 [1] NCCL INFO Setting affinity for GPU 1 to ff,ffffffff,ffff0000,00000000,00ffffff,ffffffff cnode7-009:270309:280008 [1] NCCL INFO NVLS multicast support is available on dev 1 cnode7-008:628126:637787 [3] NCCL INFO Setting affinity for GPU 3 to ff,ffffffff,ffff0000,00000000,00ffffff,ffffffff cnode7-008:628126:637787 [3] NCCL INFO NVLS multicast support is available on dev 3 cnode7-008:628130:637920 [7] NCCL INFO Setting affinity for GPU 7 to ffffffff,ffffff00,00000000,0000ffff,ffffffff,ff000000,00000000 cnode7-008:628130:637920 [7] NCCL INFO NVLS multicast support is available on dev 7 cnode7-008:628128:637782 [5] NCCL INFO Setting affinity for GPU 5 to ffffffff,ffffff00,00000000,0000ffff,ffffffff,ff000000,00000000 cnode7-008:628128:637782 [5] NCCL INFO NVLS multicast support is available on dev 5 cnode7-008:628129:637512 [6] NCCL INFO Setting affinity for GPU 6 to ffffffff,ffffff00,00000000,0000ffff,ffffffff,ff000000,00000000 cnode7-008:628129:637512 [6] NCCL INFO NVLS multicast support is available on dev 6 cnode7-008:628125:637915 [2] NCCL INFO Setting affinity for GPU 2 to ff,ffffffff,ffff0000,00000000,00ffffff,ffffffff cnode7-008:628125:637915 [2] NCCL INFO NVLS multicast support is available on dev 2 cnode7-008:628125:637915 [2] NCCL INFO comm 0x5555c0f2fd80 rank 2 nRanks 16 nNodes 2 localRanks 8 localRank 2 MNNVL 0 cnode7-008:628125:637915 [2] NCCL INFO NVLS Head 0: 0 8 cnode7-008:628125:637915 [2] NCCL INFO NVLS Head 1: 1 9 cnode7-008:628125:637915 [2] NCCL INFO NVLS Head 2: 2 10 cnode7-008:628125:637915 [2] NCCL INFO NVLS Head 3: 3 11 cnode7-008:628125:637915 [2] NCCL INFO NVLS Head 4: 4 12 cnode7-008:628125:637915 [2] NCCL INFO NVLS Head 5: 5 13 cnode7-008:628125:637915 [2] NCCL INFO NVLS Head 6: 6 14 cnode7-008:628125:637915 [2] NCCL INFO NVLS Head 7: 7 15 cnode7-008:628125:637915 [2] NCCL INFO Trees [0] 3/-1/-1->2->1 [1] 3/-1/-1->2->1 [2] 3/10/-1->2->-1 [3] -1/-1/-1->2->1 [4] 3/-1/-1->2->1 [5] 3/-1/-1->2->1 [6] 3/-1/-1->2->1 [7] 3/-1/-1->2->1 [8] 3/-1/-1->2->1 [9] 3/-1/-1->2->1 [10] 3/-1/-1->2->10 [11] -1/-1/-1->2->1 [12] 3/-1/-1->2->1 [13] 3/-1/-1->2->1 [14] 3/-1/-1->2->1 [15] 3/-1/-1->2->1 cnode7-008:628125:637915 [2] NCCL INFO P2P Chunksize set to 131072 cnode7-008:628128:637782 [5] NCCL INFO comm 0x5555c0f235b0 rank 5 nRanks 16 nNodes 2 localRanks 8 localRank 5 MNNVL 0 cnode7-008:628128:637782 [5] NCCL INFO NVLS Head 0: 0 8 cnode7-008:628128:637782 [5] NCCL INFO NVLS Head 1: 1 9 cnode7-008:628128:637782 [5] NCCL INFO NVLS Head 2: 2 10 cnode7-008:628128:637782 [5] NCCL INFO NVLS Head 3: 3 11 cnode7-008:628128:637782 [5] NCCL INFO NVLS Head 4: 4 12 cnode7-008:628128:637782 [5] NCCL INFO NVLS Head 5: 5 13 cnode7-008:628128:637782 [5] NCCL INFO NVLS Head 6: 6 14 cnode7-008:628128:637782 [5] NCCL INFO NVLS Head 7: 7 15 cnode7-008:628128:637782 [5] NCCL INFO Trees [0] 6/-1/-1->5->4 [1] 6/-1/-1->5->4 [2] 6/-1/-1->5->4 [3] 6/-1/-1->5->4 [4] 6/-1/-1->5->4 [5] 6/13/-1->5->-1 [6] -1/-1/-1->5->4 [7] 6/-1/-1->5->4 [8] 6/-1/-1->5->4 [9] 6/-1/-1->5->4 [10] 6/-1/-1->5->4 [11] 6/-1/-1->5->4 [12] 6/-1/-1->5->4 [13] 6/-1/-1->5->13 [14] -1/-1/-1->5->4 [15] 6/-1/-1->5->4 cnode7-008:628128:637782 [5] NCCL INFO P2P Chunksize set to 131072 cnode7-008:628129:637512 [6] NCCL INFO comm 0x5555c0eeb970 rank 6 nRanks 16 nNodes 2 localRanks 8 localRank 6 MNNVL 0 cnode7-008:628129:637512 [6] NCCL INFO NVLS Head 0: 0 8 cnode7-008:628129:637512 [6] NCCL INFO NVLS Head 1: 1 9 cnode7-008:628129:637512 [6] NCCL INFO NVLS Head 2: 2 10 cnode7-008:628129:637512 [6] NCCL INFO NVLS Head 3: 3 11 cnode7-008:628129:637512 [6] NCCL INFO NVLS Head 4: 4 12 cnode7-008:628129:637512 [6] NCCL INFO NVLS Head 5: 5 13 cnode7-008:628129:637512 [6] NCCL INFO NVLS Head 6: 6 14 cnode7-008:628129:637512 [6] NCCL INFO NVLS Head 7: 7 15 cnode7-008:628129:637512 [6] NCCL INFO Trees [0] 7/-1/-1->6->5 [1] 7/-1/-1->6->5 [2] 7/-1/-1->6->5 [3] 7/-1/-1->6->5 [4] 7/-1/-1->6->5 [5] 7/-1/-1->6->5 [6] 7/14/-1->6->-1 [7] -1/-1/-1->6->5 [8] 7/-1/-1->6->5 [9] 7/-1/-1->6->5 [10] 7/-1/-1->6->5 [11] 7/-1/-1->6->5 [12] 7/-1/-1->6->5 [13] 7/-1/-1->6->5 [14] 7/-1/-1->6->14 [15] -1/-1/-1->6->5 cnode7-008:628129:637512 [6] NCCL INFO P2P Chunksize set to 131072 cnode7-008:628127:637497 [4] NCCL INFO Setting affinity for GPU 4 to ffffffff,ffffff00,00000000,0000ffff,ffffffff,ff000000,00000000 cnode7-008:628127:637497 [4] NCCL INFO NVLS multicast support is available on dev 4 cnode7-008:628127:637497 [4] NCCL INFO comm 0x5555c0f3bf20 rank 4 nRanks 16 nNodes 2 localRanks 8 localRank 4 MNNVL 0 cnode7-008:628127:637497 [4] NCCL INFO NVLS Head 0: 0 8 cnode7-008:628127:637497 [4] NCCL INFO NVLS Head 1: 1 9 cnode7-008:628127:637497 [4] NCCL INFO NVLS Head 2: 2 10 cnode7-008:628127:637497 [4] NCCL INFO NVLS Head 3: 3 11 cnode7-008:628127:637497 [4] NCCL INFO NVLS Head 4: 4 12 cnode7-008:628127:637497 [4] NCCL INFO NVLS Head 5: 5 13 cnode7-008:628127:637497 [4] NCCL INFO NVLS Head 6: 6 14 cnode7-008:628127:637497 [4] NCCL INFO NVLS Head 7: 7 15 cnode7-008:628127:637497 [4] NCCL INFO Trees [0] 5/-1/-1->4->3 [1] 5/-1/-1->4->3 [2] 5/-1/-1->4->3 [3] 5/-1/-1->4->3 [4] 5/12/-1->4->-1 [5] -1/-1/-1->4->3 [6] 5/-1/-1->4->3 [7] 5/-1/-1->4->3 [8] 5/-1/-1->4->3 [9] 5/-1/-1->4->3 [10] 5/-1/-1->4->3 [11] 5/-1/-1->4->3 [12] 5/-1/-1->4->12 [13] -1/-1/-1->4->3 [14] 5/-1/-1->4->3 [15] 5/-1/-1->4->3 cnode7-008:628127:637497 [4] NCCL INFO P2P Chunksize set to 131072 cnode7-009:270311:279721 [3] NCCL INFO comm 0x5555c0f259a0 rank 11 nRanks 16 nNodes 2 localRanks 8 localRank 3 MNNVL 0 cnode7-009:270311:279721 [3] NCCL INFO Trees [0] 12/-1/-1->11->10 [1] 12/-1/-1->11->10 [2] 12/-1/-1->11->10 [3] 12/-1/-1->11->3 [4] -1/-1/-1->11->10 [5] 12/-1/-1->11->10 [6] 12/-1/-1->11->10 [7] 12/-1/-1->11->10 [8] 12/-1/-1->11->10 [9] 12/-1/-1->11->10 [10] 12/-1/-1->11->10 [11] 12/3/-1->11->-1 [12] -1/-1/-1->11->10 [13] 12/-1/-1->11->10 [14] 12/-1/-1->11->10 [15] 12/-1/-1->11->10 cnode7-009:270311:279721 [3] NCCL INFO P2P Chunksize set to 131072 cnode7-008:628126:637787 [3] NCCL INFO comm 0x5555be768d90 rank 3 nRanks 16 nNodes 2 localRanks 8 localRank 3 MNNVL 0 cnode7-008:628126:637787 [3] NCCL INFO NVLS Head 0: 0 8 cnode7-008:628126:637787 [3] NCCL INFO NVLS Head 1: 1 9 cnode7-008:628126:637787 [3] NCCL INFO NVLS Head 2: 2 10 cnode7-008:628126:637787 [3] NCCL INFO NVLS Head 3: 3 11 cnode7-008:628126:637787 [3] NCCL INFO NVLS Head 4: 4 12 cnode7-008:628126:637787 [3] NCCL INFO NVLS Head 5: 5 13 cnode7-008:628126:637787 [3] NCCL INFO NVLS Head 6: 6 14 cnode7-008:628126:637787 [3] NCCL INFO NVLS Head 7: 7 15 cnode7-008:628126:637787 [3] NCCL INFO Trees [0] 4/-1/-1->3->2 [1] 4/-1/-1->3->2 [2] 4/-1/-1->3->2 [3] 4/11/-1->3->-1 [4] -1/-1/-1->3->2 [5] 4/-1/-1->3->2 [6] 4/-1/-1->3->2 [7] 4/-1/-1->3->2 [8] 4/-1/-1->3->2 [9] 4/-1/-1->3->2 [10] 4/-1/-1->3->2 [11] 4/-1/-1->3->11 [12] -1/-1/-1->3->2 [13] 4/-1/-1->3->2 [14] 4/-1/-1->3->2 [15] 4/-1/-1->3->2 cnode7-008:628126:637787 [3] NCCL INFO P2P Chunksize set to 131072 cnode7-009:270312:279866 [4] NCCL INFO comm 0x5555c0f25440 rank 12 nRanks 16 nNodes 2 localRanks 8 localRank 4 MNNVL 0 cnode7-009:270312:279866 [4] NCCL INFO Trees [0] 13/-1/-1->12->11 [1] 13/-1/-1->12->11 [2] 13/-1/-1->12->11 [3] 13/-1/-1->12->11 [4] 13/-1/-1->12->4 [5] -1/-1/-1->12->11 [6] 13/-1/-1->12->11 [7] 13/-1/-1->12->11 [8] 13/-1/-1->12->11 [9] 13/-1/-1->12->11 [10] 13/-1/-1->12->11 [11] 13/-1/-1->12->11 [12] 13/4/-1->12->-1 [13] -1/-1/-1->12->11 [14] 13/-1/-1->12->11 [15] 13/-1/-1->12->11 cnode7-009:270312:279866 [4] NCCL INFO P2P Chunksize set to 131072 cnode7-008:628123:637496 [0] NCCL INFO Setting affinity for GPU 0 to ff,ffffffff,ffff0000,00000000,00ffffff,ffffffff cnode7-008:628123:637496 [0] NCCL INFO NVLS multicast support is available on dev 0 cnode7-008:628123:637496 [0] NCCL INFO comm 0x5555b6f0a570 rank 0 nRanks 16 nNodes 2 localRanks 8 localRank 0 MNNVL 0 cnode7-008:628123:637496 [0] NCCL INFO NVLS Head 0: 0 8 cnode7-008:628123:637496 [0] NCCL INFO NVLS Head 1: 1 9 cnode7-008:628123:637496 [0] NCCL INFO NVLS Head 2: 2 10 cnode7-008:628123:637496 [0] NCCL INFO NVLS Head 3: 3 11 cnode7-008:628123:637496 [0] NCCL INFO NVLS Head 4: 4 12 cnode7-008:628123:637496 [0] NCCL INFO NVLS Head 5: 5 13 cnode7-008:628123:637496 [0] NCCL INFO NVLS Head 6: 6 14 cnode7-008:628123:637496 [0] NCCL INFO NVLS Head 7: 7 15 cnode7-008:628123:637496 [0] NCCL INFO Channel 00/16 : 0 7 6 5 4 3 2 1 9 10 11 12 13 14 15 8 cnode7-008:628123:637496 [0] NCCL INFO Channel 01/16 : 0 8 15 14 13 12 11 10 9 1 2 3 4 5 6 7 cnode7-008:628123:637496 [0] NCCL INFO Channel 02/16 : 0 7 6 5 4 3 11 12 13 14 15 8 9 10 2 1 cnode7-008:628123:637496 [0] NCCL INFO Channel 03/16 : 0 1 2 10 9 8 15 14 13 12 11 3 4 5 6 7 cnode7-008:628123:637496 [0] NCCL INFO Channel 04/16 : 0 7 6 5 13 14 15 8 9 10 11 12 4 3 2 1 cnode7-008:628123:637496 [0] NCCL INFO Channel 05/16 : 0 1 2 3 4 12 11 10 9 8 15 14 13 5 6 7 cnode7-008:628123:637496 [0] NCCL INFO Channel 06/16 : 0 7 15 8 9 10 11 12 13 14 6 5 4 3 2 1 cnode7-008:628123:637496 [0] NCCL INFO Channel 07/16 : 0 1 2 3 4 5 6 14 13 12 11 10 9 8 15 7 cnode7-008:628123:637496 [0] NCCL INFO Channel 08/16 : 0 7 6 5 4 3 2 1 9 10 11 12 13 14 15 8 cnode7-008:628123:637496 [0] NCCL INFO Channel 09/16 : 0 8 15 14 13 12 11 10 9 1 2 3 4 5 6 7 cnode7-008:628123:637496 [0] NCCL INFO Channel 10/16 : 0 7 6 5 4 3 11 12 13 14 15 8 9 10 2 1 cnode7-008:628123:637496 [0] NCCL INFO Channel 11/16 : 0 1 2 10 9 8 15 14 13 12 11 3 4 5 6 7 cnode7-008:628123:637496 [0] NCCL INFO Channel 12/16 : 0 7 6 5 13 14 15 8 9 10 11 12 4 3 2 1 cnode7-008:628123:637496 [0] NCCL INFO Channel 13/16 : 0 1 2 3 4 12 11 10 9 8 15 14 13 5 6 7 cnode7-008:628123:637496 [0] NCCL INFO Channel 14/16 : 0 7 15 8 9 10 11 12 13 14 6 5 4 3 2 1 cnode7-008:628123:637496 [0] NCCL INFO Channel 15/16 : 0 1 2 3 4 5 6 14 13 12 11 10 9 8 15 7 cnode7-008:628123:637496 [0] NCCL INFO Trees [0] 1/8/-1->0->-1 [1] -1/-1/-1->0->7 [2] 1/-1/-1->0->7 [3] 1/-1/-1->0->7 [4] 1/-1/-1->0->7 [5] 1/-1/-1->0->7 [6] 1/-1/-1->0->7 [7] 1/-1/-1->0->7 [8] 1/-1/-1->0->8 [9] -1/-1/-1->0->7 [10] 1/-1/-1->0->7 [11] 1/-1/-1->0->7 [12] 1/-1/-1->0->7 [13] 1/-1/-1->0->7 [14] 1/-1/-1->0->7 [15] 1/-1/-1->0->7 cnode7-008:628123:637496 [0] NCCL INFO P2P Chunksize set to 131072 cnode7-008:628130:637920 [7] NCCL INFO comm 0x5555c0efc560 rank 7 nRanks 16 nNodes 2 localRanks 8 localRank 7 MNNVL 0 cnode7-008:628130:637920 [7] NCCL INFO NVLS Head 0: 0 8 cnode7-008:628130:637920 [7] NCCL INFO NVLS Head 1: 1 9 cnode7-008:628130:637920 [7] NCCL INFO NVLS Head 2: 2 10 cnode7-008:628130:637920 [7] NCCL INFO NVLS Head 3: 3 11 cnode7-008:628130:637920 [7] NCCL INFO NVLS Head 4: 4 12 cnode7-008:628130:637920 [7] NCCL INFO NVLS Head 5: 5 13 cnode7-008:628130:637920 [7] NCCL INFO NVLS Head 6: 6 14 cnode7-008:628130:637920 [7] NCCL INFO NVLS Head 7: 7 15 cnode7-008:628130:637920 [7] NCCL INFO Trees [0] -1/-1/-1->7->6 [1] 0/-1/-1->7->6 [2] 0/-1/-1->7->6 [3] 0/-1/-1->7->6 [4] 0/-1/-1->7->6 [5] 0/-1/-1->7->6 [6] 0/-1/-1->7->6 [7] 0/15/-1->7->-1 [8] -1/-1/-1->7->6 [9] 0/-1/-1->7->6 [10] 0/-1/-1->7->6 [11] 0/-1/-1->7->6 [12] 0/-1/-1->7->6 [13] 0/-1/-1->7->6 [14] 0/-1/-1->7->6 [15] 0/-1/-1->7->15 cnode7-008:628130:637920 [7] NCCL INFO P2P Chunksize set to 131072 cnode7-008:628124:637498 [1] NCCL INFO Setting affinity for GPU 1 to ff,ffffffff,ffff0000,00000000,00ffffff,ffffffff cnode7-008:628124:637498 [1] NCCL INFO NVLS multicast support is available on dev 1 cnode7-008:628124:637498 [1] NCCL INFO comm 0x5555c0f0dbb0 rank 1 nRanks 16 nNodes 2 localRanks 8 localRank 1 MNNVL 0 cnode7-008:628124:637498 [1] NCCL INFO NVLS Head 0: 0 8 cnode7-008:628124:637498 [1] NCCL INFO NVLS Head 1: 1 9 cnode7-008:628124:637498 [1] NCCL INFO NVLS Head 2: 2 10 cnode7-008:628124:637498 [1] NCCL INFO NVLS Head 3: 3 11 cnode7-008:628124:637498 [1] NCCL INFO NVLS Head 4: 4 12 cnode7-008:628124:637498 [1] NCCL INFO NVLS Head 5: 5 13 cnode7-008:628124:637498 [1] NCCL INFO NVLS Head 6: 6 14 cnode7-008:628124:637498 [1] NCCL INFO NVLS Head 7: 7 15 cnode7-008:628124:637498 [1] NCCL INFO Trees [0] 2/-1/-1->1->0 [1] 2/9/-1->1->-1 [2] -1/-1/-1->1->0 [3] 2/-1/-1->1->0 [4] 2/-1/-1->1->0 [5] 2/-1/-1->1->0 [6] 2/-1/-1->1->0 [7] 2/-1/-1->1->0 [8] 2/-1/-1->1->0 [9] 2/-1/-1->1->9 [10] -1/-1/-1->1->0 [11] 2/-1/-1->1->0 [12] 2/-1/-1->1->0 [13] 2/-1/-1->1->0 [14] 2/-1/-1->1->0 [15] 2/-1/-1->1->0 cnode7-008:628124:637498 [1] NCCL INFO P2P Chunksize set to 131072 cnode7-008:628123:637496 [0] NCCL INFO Channel 03/0 : 0[0] -> 1[1] via P2P/CUMEM cnode7-008:628123:637496 [0] NCCL INFO Channel 05/0 : 0[0] -> 1[1] via P2P/CUMEM cnode7-008:628123:637496 [0] NCCL INFO Channel 07/0 : 0[0] -> 1[1] via P2P/CUMEM cnode7-008:628123:637496 [0] NCCL INFO Channel 11/0 : 0[0] -> 1[1] via P2P/CUMEM cnode7-008:628123:637496 [0] NCCL INFO Channel 13/0 : 0[0] -> 1[1] via P2P/CUMEM cnode7-008:628123:637496 [0] NCCL INFO Channel 15/0 : 0[0] -> 1[1] via P2P/CUMEM cnode7-009:270309:280008 [1] NCCL INFO comm 0x5555d4f28520 rank 9 nRanks 16 nNodes 2 localRanks 8 localRank 1 MNNVL 0 cnode7-009:270309:280008 [1] NCCL INFO Trees [0] 10/-1/-1->9->8 [1] 10/-1/-1->9->1 [2] -1/-1/-1->9->8 [3] 10/-1/-1->9->8 [4] 10/-1/-1->9->8 [5] 10/-1/-1->9->8 [6] 10/-1/-1->9->8 [7] 10/-1/-1->9->8 [8] 10/-1/-1->9->8 [9] 10/1/-1->9->-1 [10] -1/-1/-1->9->8 [11] 10/-1/-1->9->8 [12] 10/-1/-1->9->8 [13] 10/-1/-1->9->8 [14] 10/-1/-1->9->8 [15] 10/-1/-1->9->8 cnode7-009:270309:280008 [1] NCCL INFO P2P Chunksize set to 131072 cnode7-009:270308:279372 [0] NCCL INFO comm 0x5555b6f4b630 rank 8 nRanks 16 nNodes 2 localRanks 8 localRank 0 MNNVL 0 cnode7-009:270308:279372 [0] NCCL INFO Trees [0] 9/-1/-1->8->0 [1] -1/-1/-1->8->15 [2] 9/-1/-1->8->15 [3] 9/-1/-1->8->15 [4] 9/-1/-1->8->15 [5] 9/-1/-1->8->15 [6] 9/-1/-1->8->15 [7] 9/-1/-1->8->15 [8] 9/0/-1->8->-1 [9] -1/-1/-1->8->15 [10] 9/-1/-1->8->15 [11] 9/-1/-1->8->15 [12] 9/-1/-1->8->15 [13] 9/-1/-1->8->15 [14] 9/-1/-1->8->15 [15] 9/-1/-1->8->15 cnode7-009:270308:279372 [0] NCCL INFO P2P Chunksize set to 131072 cnode7-009:270310:279373 [2] NCCL INFO comm 0x5555c0f31ff0 rank 10 nRanks 16 nNodes 2 localRanks 8 localRank 2 MNNVL 0 cnode7-009:270310:279373 [2] NCCL INFO Trees [0] 11/-1/-1->10->9 [1] 11/-1/-1->10->9 [2] 11/-1/-1->10->2 [3] -1/-1/-1->10->9 [4] 11/-1/-1->10->9 [5] 11/-1/-1->10->9 [6] 11/-1/-1->10->9 [7] 11/-1/-1->10->9 [8] 11/-1/-1->10->9 [9] 11/-1/-1->10->9 [10] 11/2/-1->10->-1 [11] -1/-1/-1->10->9 [12] 11/-1/-1->10->9 [13] 11/-1/-1->10->9 [14] 11/-1/-1->10->9 [15] 11/-1/-1->10->9 cnode7-009:270310:279373 [2] NCCL INFO P2P Chunksize set to 131072 cnode7-009:270315:280163 [7] NCCL INFO comm 0x5555c0eedd70 rank 15 nRanks 16 nNodes 2 localRanks 8 localRank 7 MNNVL 0 cnode7-009:270315:280163 [7] NCCL INFO Trees [0] -1/-1/-1->15->14 [1] 8/-1/-1->15->14 [2] 8/-1/-1->15->14 [3] 8/-1/-1->15->14 [4] 8/-1/-1->15->14 [5] 8/-1/-1->15->14 [6] 8/-1/-1->15->14 [7] 8/-1/-1->15->7 [8] -1/-1/-1->15->14 [9] 8/-1/-1->15->14 [10] 8/-1/-1->15->14 [11] 8/-1/-1->15->14 [12] 8/-1/-1->15->14 [13] 8/-1/-1->15->14 [14] 8/-1/-1->15->14 [15] 8/7/-1->15->-1 cnode7-009:270315:280163 [7] NCCL INFO P2P Chunksize set to 131072 cnode7-009:270313:279722 [5] NCCL INFO comm 0x5555c0f35c90 rank 13 nRanks 16 nNodes 2 localRanks 8 localRank 5 MNNVL 0 cnode7-009:270313:279722 [5] NCCL INFO Trees [0] 14/-1/-1->13->12 [1] 14/-1/-1->13->12 [2] 14/-1/-1->13->12 [3] 14/-1/-1->13->12 [4] 14/-1/-1->13->12 [5] 14/-1/-1->13->5 [6] -1/-1/-1->13->12 [7] 14/-1/-1->13->12 [8] 14/-1/-1->13->12 [9] 14/-1/-1->13->12 [10] 14/-1/-1->13->12 [11] 14/-1/-1->13->12 [12] 14/-1/-1->13->12 [13] 14/5/-1->13->-1 [14] -1/-1/-1->13->12 [15] 14/-1/-1->13->12 cnode7-009:270313:279722 [5] NCCL INFO P2P Chunksize set to 131072 cnode7-009:270314:279443 [6] NCCL INFO comm 0x5555c0f38de0 rank 14 nRanks 16 nNodes 2 localRanks 8 localRank 6 MNNVL 0 cnode7-009:270314:279443 [6] NCCL INFO Trees [0] 15/-1/-1->14->13 [1] 15/-1/-1->14->13 [2] 15/-1/-1->14->13 [3] 15/-1/-1->14->13 [4] 15/-1/-1->14->13 [5] 15/-1/-1->14->13 [6] 15/-1/-1->14->6 [7] -1/-1/-1->14->13 [8] 15/-1/-1->14->13 [9] 15/-1/-1->14->13 [10] 15/-1/-1->14->13 [11] 15/-1/-1->14->13 [12] 15/-1/-1->14->13 [13] 15/-1/-1->14->13 [14] 15/6/-1->14->-1 [15] -1/-1/-1->14->13 cnode7-009:270314:279443 [6] NCCL INFO P2P Chunksize set to 131072 cnode7-008:628124:637498 [1] NCCL INFO Channel 01/0 : 1[1] -> 2[2] via P2P/CUMEM cnode7-008:628124:637498 [1] NCCL INFO Channel 03/0 : 1[1] -> 2[2] via P2P/CUMEM cnode7-008:628124:637498 [1] NCCL INFO Channel 05/0 : 1[1] -> 2[2] via P2P/CUMEM cnode7-008:628124:637498 [1] NCCL INFO Channel 07/0 : 1[1] -> 2[2] via P2P/CUMEM cnode7-009:270310:279373 [2] NCCL INFO Channel 00/0 : 10[2] -> 11[3] via P2P/CUMEM cnode7-009:270310:279373 [2] NCCL INFO Channel 04/0 : 10[2] -> 11[3] via P2P/CUMEM cnode7-008:628129:637512 [6] NCCL INFO Channel 01/0 : 6[6] -> 7[7] via P2P/CUMEM cnode7-008:628129:637512 [6] NCCL INFO Channel 03/0 : 6[6] -> 7[7] via P2P/CUMEM cnode7-008:628129:637512 [6] NCCL INFO Channel 05/0 : 6[6] -> 7[7] via P2P/CUMEM cnode7-008:628129:637512 [6] NCCL INFO Channel 09/0 : 6[6] -> 7[7] via P2P/CUMEM cnode7-008:628129:637512 [6] NCCL INFO Channel 11/0 : 6[6] -> 7[7] via P2P/CUMEM cnode7-008:628129:637512 [6] NCCL INFO Channel 13/0 : 6[6] -> 7[7] via P2P/CUMEM cnode7-008:628126:637787 [3] NCCL INFO Channel 01/0 : 3[3] -> 4[4] via P2P/CUMEM cnode7-008:628126:637787 [3] NCCL INFO Channel 03/0 : 3[3] -> 4[4] via P2P/CUMEM cnode7-008:628126:637787 [3] NCCL INFO Channel 05/0 : 3[3] -> 4[4] via P2P/CUMEM cnode7-008:628126:637787 [3] NCCL INFO Channel 07/0 : 3[3] -> 4[4] via P2P/CUMEM cnode7-008:628126:637787 [3] NCCL INFO Channel 09/0 : 3[3] -> 4[4] via P2P/CUMEM cnode7-008:628126:637787 [3] NCCL INFO Channel 11/0 : 3[3] -> 4[4] via P2P/CUMEM cnode7-008:628126:637787 [3] NCCL INFO Channel 13/0 : 3[3] -> 4[4] via P2P/CUMEM cnode7-008:628126:637787 [3] NCCL INFO Channel 15/0 : 3[3] -> 4[4] via P2P/CUMEM cnode7-008:628126:637787 [3] NCCL INFO Channel 03/0 : 11[3] -> 3[3] [receive] via NET/IB/3/GDRDMA cnode7-008:628126:637787 [3] NCCL INFO Channel 11/0 : 11[3] -> 3[3] [receive] via NET/IB/3/GDRDMA cnode7-008:628126:637787 [3] NCCL INFO Channel 02/0 : 3[3] -> 11[3] [send] via NET/IB/3/GDRDMA cnode7-008:628126:637787 [3] NCCL INFO Channel 10/0 : 3[3] -> 11[3] [send] via NET/IB/3/GDRDMA cnode7-009:270308:279372 [0] NCCL INFO Channel 02/0 : 8[0] -> 9[1] via P2P/CUMEM cnode7-009:270308:279372 [0] NCCL INFO Channel 04/0 : 8[0] -> 9[1] via P2P/CUMEM cnode7-009:270308:279372 [0] NCCL INFO Channel 06/0 : 8[0] -> 9[1] via P2P/CUMEM cnode7-009:270308:279372 [0] NCCL INFO Channel 10/0 : 8[0] -> 9[1] via P2P/CUMEM cnode7-009:270308:279372 [0] NCCL INFO Channel 12/0 : 8[0] -> 9[1] via P2P/CUMEM cnode7-009:270308:279372 [0] NCCL INFO Channel 14/0 : 8[0] -> 9[1] via P2P/CUMEM cnode7-009:270308:279372 [0] NCCL INFO Channel 01/0 : 8[0] -> 15[7] via P2P/CUMEM cnode7-009:270308:279372 [0] NCCL INFO Channel 03/0 : 8[0] -> 15[7] via P2P/CUMEM cnode7-009:270308:279372 [0] NCCL INFO Channel 05/0 : 8[0] -> 15[7] via P2P/CUMEM cnode7-009:270308:279372 [0] NCCL INFO Channel 07/0 : 8[0] -> 15[7] via P2P/CUMEM cnode7-009:270308:279372 [0] NCCL INFO Channel 09/0 : 8[0] -> 15[7] via P2P/CUMEM cnode7-009:270308:279372 [0] NCCL INFO Channel 11/0 : 8[0] -> 15[7] via P2P/CUMEM cnode7-009:270308:279372 [0] NCCL INFO Channel 13/0 : 8[0] -> 15[7] via P2P/CUMEM cnode7-009:270308:279372 [0] NCCL INFO Channel 15/0 : 8[0] -> 15[7] via P2P/CUMEM cnode7-009:270311:279721 [3] NCCL INFO Channel 00/0 : 11[3] -> 12[4] via P2P/CUMEM cnode7-009:270311:279721 [3] NCCL INFO Channel 02/0 : 11[3] -> 12[4] via P2P/CUMEM cnode7-009:270311:279721 [3] NCCL INFO Channel 04/0 : 11[3] -> 12[4] via P2P/CUMEM cnode7-009:270311:279721 [3] NCCL INFO Channel 06/0 : 11[3] -> 12[4] via P2P/CUMEM cnode7-009:270311:279721 [3] NCCL INFO Channel 08/0 : 11[3] -> 12[4] via P2P/CUMEM cnode7-009:270311:279721 [3] NCCL INFO Channel 10/0 : 11[3] -> 12[4] via P2P/CUMEM cnode7-009:270311:279721 [3] NCCL INFO Channel 12/0 : 11[3] -> 12[4] via P2P/CUMEM cnode7-009:270311:279721 [3] NCCL INFO Channel 14/0 : 11[3] -> 12[4] via P2P/CUMEM cnode7-009:270311:279721 [3] NCCL INFO Channel 02/0 : 3[3] -> 11[3] [receive] via NET/IB/3/GDRDMA cnode7-009:270311:279721 [3] NCCL INFO Channel 10/0 : 3[3] -> 11[3] [receive] via NET/IB/3/GDRDMA cnode7-009:270311:279721 [3] NCCL INFO Channel 03/0 : 11[3] -> 3[3] [send] via NET/IB/3/GDRDMA cnode7-009:270311:279721 [3] NCCL INFO Channel 11/0 : 11[3] -> 3[3] [send] via NET/IB/3/GDRDMA cnode7-009:270312:279866 [4] NCCL INFO Channel 00/0 : 12[4] -> 13[5] via P2P/CUMEM cnode7-009:270312:279866 [4] NCCL INFO Channel 02/0 : 12[4] -> 13[5] via P2P/CUMEM cnode7-009:270312:279866 [4] NCCL INFO Channel 06/0 : 12[4] -> 13[5] via P2P/CUMEM cnode7-009:270312:279866 [4] NCCL INFO Channel 08/0 : 12[4] -> 13[5] via P2P/CUMEM cnode7-009:270312:279866 [4] NCCL INFO Channel 10/0 : 12[4] -> 13[5] via P2P/CUMEM cnode7-009:270312:279866 [4] NCCL INFO Channel 14/0 : 12[4] -> 13[5] via P2P/CUMEM cnode7-009:270312:279866 [4] NCCL INFO Channel 05/0 : 4[4] -> 12[4] [receive] via NET/IB/4/GDRDMA cnode7-009:270312:279866 [4] NCCL INFO Channel 13/0 : 4[4] -> 12[4] [receive] via NET/IB/4/GDRDMA cnode7-009:270312:279866 [4] NCCL INFO Channel 04/0 : 12[4] -> 4[4] [send] via NET/IB/4/GDRDMA cnode7-009:270312:279866 [4] NCCL INFO Channel 12/0 : 12[4] -> 4[4] [send] via NET/IB/4/GDRDMA cnode7-009:270309:280008 [1] NCCL INFO Channel 00/0 : 9[1] -> 10[2] via P2P/CUMEM cnode7-009:270309:280008 [1] NCCL INFO Channel 02/0 : 9[1] -> 10[2] via P2P/CUMEM cnode7-009:270309:280008 [1] NCCL INFO Channel 04/0 : 9[1] -> 10[2] via P2P/CUMEM cnode7-009:270309:280008 [1] NCCL INFO Channel 06/0 : 9[1] -> 10[2] via P2P/CUMEM cnode7-009:270309:280008 [1] NCCL INFO Channel 08/0 : 9[1] -> 10[2] via P2P/CUMEM cnode7-009:270309:280008 [1] NCCL INFO Channel 10/0 : 9[1] -> 10[2] via P2P/CUMEM cnode7-009:270309:280008 [1] NCCL INFO Channel 12/0 : 9[1] -> 10[2] via P2P/CUMEM cnode7-009:270309:280008 [1] NCCL INFO Channel 14/0 : 9[1] -> 10[2] via P2P/CUMEM cnode7-009:270309:280008 [1] NCCL INFO Channel 00/0 : 1[1] -> 9[1] [receive] via NET/IB/1/GDRDMA cnode7-009:270309:280008 [1] NCCL INFO Channel 08/0 : 1[1] -> 9[1] [receive] via NET/IB/1/GDRDMA cnode7-009:270309:280008 [1] NCCL INFO Channel 01/0 : 9[1] -> 1[1] [send] via NET/IB/1/GDRDMA cnode7-009:270309:280008 [1] NCCL INFO Channel 09/0 : 9[1] -> 1[1] [send] via NET/IB/1/GDRDMA cnode7-009:270309:280008 [1] NCCL INFO Channel 03/0 : 9[1] -> 8[0] via P2P/CUMEM cnode7-009:270309:280008 [1] NCCL INFO Channel 05/0 : 9[1] -> 8[0] via P2P/CUMEM cnode7-009:270309:280008 [1] NCCL INFO Channel 07/0 : 9[1] -> 8[0] via P2P/CUMEM cnode7-009:270309:280008 [1] NCCL INFO Channel 11/0 : 9[1] -> 8[0] via P2P/CUMEM cnode7-009:270309:280008 [1] NCCL INFO Channel 13/0 : 9[1] -> 8[0] via P2P/CUMEM cnode7-009:270309:280008 [1] NCCL INFO Channel 15/0 : 9[1] -> 8[0] via P2P/CUMEM cnode7-008:628125:637915 [2] NCCL INFO Channel 01/0 : 2[2] -> 3[3] via P2P/CUMEM cnode7-008:628125:637915 [2] NCCL INFO Channel 05/0 : 2[2] -> 3[3] via P2P/CUMEM cnode7-008:628125:637915 [2] NCCL INFO Channel 07/0 : 2[2] -> 3[3] via P2P/CUMEM cnode7-008:628125:637915 [2] NCCL INFO Channel 09/0 : 2[2] -> 3[3] via P2P/CUMEM cnode7-008:628125:637915 [2] NCCL INFO Channel 13/0 : 2[2] -> 3[3] via P2P/CUMEM cnode7-008:628125:637915 [2] NCCL INFO Channel 15/0 : 2[2] -> 3[3] via P2P/CUMEM cnode7-008:628125:637915 [2] NCCL INFO Channel 02/0 : 10[2] -> 2[2] [receive] via NET/IB/2/GDRDMA cnode7-008:628125:637915 [2] NCCL INFO Channel 10/0 : 10[2] -> 2[2] [receive] via NET/IB/2/GDRDMA cnode7-008:628125:637915 [2] NCCL INFO Channel 03/0 : 2[2] -> 10[2] [send] via NET/IB/2/GDRDMA cnode7-008:628125:637915 [2] NCCL INFO Channel 11/0 : 2[2] -> 10[2] [send] via NET/IB/2/GDRDMA cnode7-008:628123:637496 [0] NCCL INFO Channel 00/0 : 0[0] -> 7[7] via P2P/CUMEM cnode7-008:628123:637496 [0] NCCL INFO Channel 02/0 : 0[0] -> 7[7] via P2P/CUMEM cnode7-008:628123:637496 [0] NCCL INFO Channel 04/0 : 0[0] -> 7[7] via P2P/CUMEM cnode7-008:628123:637496 [0] NCCL INFO Channel 06/0 : 0[0] -> 7[7] via P2P/CUMEM cnode7-008:628123:637496 [0] NCCL INFO Channel 08/0 : 0[0] -> 7[7] via P2P/CUMEM cnode7-008:628123:637496 [0] NCCL INFO Channel 10/0 : 0[0] -> 7[7] via P2P/CUMEM cnode7-008:628123:637496 [0] NCCL INFO Channel 12/0 : 0[0] -> 7[7] via P2P/CUMEM cnode7-008:628123:637496 [0] NCCL INFO Channel 14/0 : 0[0] -> 7[7] via P2P/CUMEM cnode7-008:628123:637496 [0] NCCL INFO Channel 00/0 : 8[0] -> 0[0] [receive] via NET/IB/0/GDRDMA cnode7-008:628123:637496 [0] NCCL INFO Channel 08/0 : 8[0] -> 0[0] [receive] via NET/IB/0/GDRDMA cnode7-008:628123:637496 [0] NCCL INFO Channel 01/0 : 0[0] -> 8[0] [send] via NET/IB/0/GDRDMA cnode7-008:628123:637496 [0] NCCL INFO Channel 09/0 : 0[0] -> 8[0] [send] via NET/IB/0/GDRDMA cnode7-008:628127:637497 [4] NCCL INFO Channel 01/0 : 4[4] -> 5[5] via P2P/CUMEM cnode7-008:628127:637497 [4] NCCL INFO Channel 03/0 : 4[4] -> 5[5] via P2P/CUMEM cnode7-008:628127:637497 [4] NCCL INFO Channel 07/0 : 4[4] -> 5[5] via P2P/CUMEM cnode7-008:628127:637497 [4] NCCL INFO Channel 09/0 : 4[4] -> 5[5] via P2P/CUMEM cnode7-008:628127:637497 [4] NCCL INFO Channel 11/0 : 4[4] -> 5[5] via P2P/CUMEM cnode7-008:628127:637497 [4] NCCL INFO Channel 15/0 : 4[4] -> 5[5] via P2P/CUMEM cnode7-008:628130:637920 [7] NCCL INFO Channel 07/0 : 15[7] -> 7[7] [receive] via NET/IB/8/GDRDMA cnode7-008:628130:637920 [7] NCCL INFO Channel 15/0 : 15[7] -> 7[7] [receive] via NET/IB/8/GDRDMA cnode7-008:628130:637920 [7] NCCL INFO Channel 06/0 : 7[7] -> 15[7] [send] via NET/IB/8/GDRDMA cnode7-008:628130:637920 [7] NCCL INFO Channel 14/0 : 7[7] -> 15[7] [send] via NET/IB/8/GDRDMA cnode7-008:628124:637498 [1] NCCL INFO Channel 09/0 : 1[1] -> 2[2] via P2P/CUMEM cnode7-008:628124:637498 [1] NCCL INFO Channel 11/0 : 1[1] -> 2[2] via P2P/CUMEM cnode7-008:628124:637498 [1] NCCL INFO Channel 13/0 : 1[1] -> 2[2] via P2P/CUMEM cnode7-008:628124:637498 [1] NCCL INFO Channel 15/0 : 1[1] -> 2[2] via P2P/CUMEM cnode7-008:628124:637498 [1] NCCL INFO Channel 01/0 : 9[1] -> 1[1] [receive] via NET/IB/1/GDRDMA cnode7-008:628124:637498 [1] NCCL INFO Channel 09/0 : 9[1] -> 1[1] [receive] via NET/IB/1/GDRDMA cnode7-008:628124:637498 [1] NCCL INFO Channel 00/0 : 1[1] -> 9[1] [send] via NET/IB/1/GDRDMA cnode7-008:628124:637498 [1] NCCL INFO Channel 08/0 : 1[1] -> 9[1] [send] via NET/IB/1/GDRDMA cnode7-009:270310:279373 [2] NCCL INFO Channel 06/0 : 10[2] -> 11[3] via P2P/CUMEM cnode7-009:270310:279373 [2] NCCL INFO Channel 08/0 : 10[2] -> 11[3] via P2P/CUMEM cnode7-009:270310:279373 [2] NCCL INFO Channel 12/0 : 10[2] -> 11[3] via P2P/CUMEM cnode7-009:270310:279373 [2] NCCL INFO Channel 14/0 : 10[2] -> 11[3] via P2P/CUMEM cnode7-009:270310:279373 [2] NCCL INFO Channel 03/0 : 2[2] -> 10[2] [receive] via NET/IB/2/GDRDMA cnode7-009:270310:279373 [2] NCCL INFO Channel 11/0 : 2[2] -> 10[2] [receive] via NET/IB/2/GDRDMA cnode7-009:270310:279373 [2] NCCL INFO Channel 02/0 : 10[2] -> 2[2] [send] via NET/IB/2/GDRDMA cnode7-009:270310:279373 [2] NCCL INFO Channel 10/0 : 10[2] -> 2[2] [send] via NET/IB/2/GDRDMA cnode7-009:270310:279373 [2] NCCL INFO Channel 01/0 : 10[2] -> 9[1] via P2P/CUMEM cnode7-009:270310:279373 [2] NCCL INFO Channel 03/0 : 10[2] -> 9[1] via P2P/CUMEM cnode7-009:270310:279373 [2] NCCL INFO Channel 05/0 : 10[2] -> 9[1] via P2P/CUMEM cnode7-009:270310:279373 [2] NCCL INFO Channel 07/0 : 10[2] -> 9[1] via P2P/CUMEM cnode7-009:270310:279373 [2] NCCL INFO Channel 09/0 : 10[2] -> 9[1] via P2P/CUMEM cnode7-009:270310:279373 [2] NCCL INFO Channel 11/0 : 10[2] -> 9[1] via P2P/CUMEM cnode7-009:270310:279373 [2] NCCL INFO Channel 13/0 : 10[2] -> 9[1] via P2P/CUMEM cnode7-009:270310:279373 [2] NCCL INFO Channel 15/0 : 10[2] -> 9[1] via P2P/CUMEM cnode7-009:270313:279722 [5] NCCL INFO Channel 00/0 : 13[5] -> 14[6] via P2P/CUMEM cnode7-009:270313:279722 [5] NCCL INFO Channel 02/0 : 13[5] -> 14[6] via P2P/CUMEM cnode7-009:270313:279722 [5] NCCL INFO Channel 04/0 : 13[5] -> 14[6] via P2P/CUMEM cnode7-009:270313:279722 [5] NCCL INFO Channel 06/0 : 13[5] -> 14[6] via P2P/CUMEM cnode7-009:270313:279722 [5] NCCL INFO Channel 08/0 : 13[5] -> 14[6] via P2P/CUMEM cnode7-009:270313:279722 [5] NCCL INFO Channel 10/0 : 13[5] -> 14[6] via P2P/CUMEM cnode7-009:270313:279722 [5] NCCL INFO Channel 12/0 : 13[5] -> 14[6] via P2P/CUMEM cnode7-009:270313:279722 [5] NCCL INFO Channel 14/0 : 13[5] -> 14[6] via P2P/CUMEM cnode7-009:270313:279722 [5] NCCL INFO Channel 04/0 : 5[5] -> 13[5] [receive] via NET/IB/6/GDRDMA cnode7-009:270313:279722 [5] NCCL INFO Channel 12/0 : 5[5] -> 13[5] [receive] via NET/IB/6/GDRDMA cnode7-009:270313:279722 [5] NCCL INFO Channel 05/0 : 13[5] -> 5[5] [send] via NET/IB/6/GDRDMA cnode7-009:270313:279722 [5] NCCL INFO Channel 13/0 : 13[5] -> 5[5] [send] via NET/IB/6/GDRDMA cnode7-008:628128:637782 [5] NCCL INFO Channel 01/0 : 5[5] -> 6[6] via P2P/CUMEM cnode7-008:628128:637782 [5] NCCL INFO Channel 03/0 : 5[5] -> 6[6] via P2P/CUMEM cnode7-008:628128:637782 [5] NCCL INFO Channel 05/0 : 5[5] -> 6[6] via P2P/CUMEM cnode7-008:628128:637782 [5] NCCL INFO Channel 07/0 : 5[5] -> 6[6] via P2P/CUMEM cnode7-008:628128:637782 [5] NCCL INFO Channel 09/0 : 5[5] -> 6[6] via P2P/CUMEM cnode7-008:628128:637782 [5] NCCL INFO Channel 11/0 : 5[5] -> 6[6] via P2P/CUMEM cnode7-008:628128:637782 [5] NCCL INFO Channel 13/0 : 5[5] -> 6[6] via P2P/CUMEM cnode7-008:628128:637782 [5] NCCL INFO Channel 15/0 : 5[5] -> 6[6] via P2P/CUMEM cnode7-008:628128:637782 [5] NCCL INFO Channel 05/0 : 13[5] -> 5[5] [receive] via NET/IB/6/GDRDMA cnode7-008:628128:637782 [5] NCCL INFO Channel 13/0 : 13[5] -> 5[5] [receive] via NET/IB/6/GDRDMA cnode7-008:628128:637782 [5] NCCL INFO Channel 04/0 : 5[5] -> 13[5] [send] via NET/IB/6/GDRDMA cnode7-008:628128:637782 [5] NCCL INFO Channel 12/0 : 5[5] -> 13[5] [send] via NET/IB/6/GDRDMA cnode7-008:628129:637512 [6] NCCL INFO Channel 06/0 : 14[6] -> 6[6] [receive] via NET/IB/7/GDRDMA cnode7-008:628129:637512 [6] NCCL INFO Channel 14/0 : 14[6] -> 6[6] [receive] via NET/IB/7/GDRDMA cnode7-008:628129:637512 [6] NCCL INFO Channel 07/0 : 6[6] -> 14[6] [send] via NET/IB/7/GDRDMA cnode7-008:628129:637512 [6] NCCL INFO Channel 15/0 : 6[6] -> 14[6] [send] via NET/IB/7/GDRDMA cnode7-008:628126:637787 [3] NCCL INFO Channel 00/0 : 3[3] -> 2[2] via P2P/CUMEM cnode7-008:628126:637787 [3] NCCL INFO Channel 04/0 : 3[3] -> 2[2] via P2P/CUMEM cnode7-008:628126:637787 [3] NCCL INFO Channel 06/0 : 3[3] -> 2[2] via P2P/CUMEM cnode7-008:628126:637787 [3] NCCL INFO Channel 08/0 : 3[3] -> 2[2] via P2P/CUMEM cnode7-008:628126:637787 [3] NCCL INFO Channel 12/0 : 3[3] -> 2[2] via P2P/CUMEM cnode7-008:628126:637787 [3] NCCL INFO Channel 14/0 : 3[3] -> 2[2] via P2P/CUMEM cnode7-009:270314:279443 [6] NCCL INFO Channel 00/0 : 14[6] -> 15[7] via P2P/CUMEM cnode7-009:270314:279443 [6] NCCL INFO Channel 02/0 : 14[6] -> 15[7] via P2P/CUMEM cnode7-009:270314:279443 [6] NCCL INFO Channel 04/0 : 14[6] -> 15[7] via P2P/CUMEM cnode7-009:270314:279443 [6] NCCL INFO Channel 08/0 : 14[6] -> 15[7] via P2P/CUMEM cnode7-009:270314:279443 [6] NCCL INFO Channel 10/0 : 14[6] -> 15[7] via P2P/CUMEM cnode7-009:270314:279443 [6] NCCL INFO Channel 12/0 : 14[6] -> 15[7] via P2P/CUMEM cnode7-009:270314:279443 [6] NCCL INFO Channel 07/0 : 6[6] -> 14[6] [receive] via NET/IB/7/GDRDMA cnode7-009:270314:279443 [6] NCCL INFO Channel 15/0 : 6[6] -> 14[6] [receive] via NET/IB/7/GDRDMA cnode7-009:270314:279443 [6] NCCL INFO Channel 06/0 : 14[6] -> 6[6] [send] via NET/IB/7/GDRDMA cnode7-009:270314:279443 [6] NCCL INFO Channel 14/0 : 14[6] -> 6[6] [send] via NET/IB/7/GDRDMA cnode7-009:270314:279443 [6] NCCL INFO Channel 01/0 : 14[6] -> 13[5] via P2P/CUMEM cnode7-009:270314:279443 [6] NCCL INFO Channel 03/0 : 14[6] -> 13[5] via P2P/CUMEM cnode7-009:270314:279443 [6] NCCL INFO Channel 05/0 : 14[6] -> 13[5] via P2P/CUMEM cnode7-009:270314:279443 [6] NCCL INFO Channel 07/0 : 14[6] -> 13[5] via P2P/CUMEM cnode7-009:270315:280163 [7] NCCL INFO Channel 06/0 : 7[7] -> 15[7] [receive] via NET/IB/8/GDRDMA cnode7-009:270315:280163 [7] NCCL INFO Channel 14/0 : 7[7] -> 15[7] [receive] via NET/IB/8/GDRDMA cnode7-009:270315:280163 [7] NCCL INFO Channel 07/0 : 15[7] -> 7[7] [send] via NET/IB/8/GDRDMA cnode7-009:270315:280163 [7] NCCL INFO Channel 15/0 : 15[7] -> 7[7] [send] via NET/IB/8/GDRDMA cnode7-009:270315:280163 [7] NCCL INFO Channel 00/0 : 15[7] -> 8[0] via P2P/CUMEM cnode7-009:270315:280163 [7] NCCL INFO Channel 02/0 : 15[7] -> 8[0] via P2P/CUMEM cnode7-009:270315:280163 [7] NCCL INFO Channel 04/0 : 15[7] -> 8[0] via P2P/CUMEM cnode7-009:270315:280163 [7] NCCL INFO Channel 06/0 : 15[7] -> 8[0] via P2P/CUMEM cnode7-009:270315:280163 [7] NCCL INFO Channel 08/0 : 15[7] -> 8[0] via P2P/CUMEM cnode7-009:270315:280163 [7] NCCL INFO Channel 10/0 : 15[7] -> 8[0] via P2P/CUMEM cnode7-009:270315:280163 [7] NCCL INFO Channel 12/0 : 15[7] -> 8[0] via P2P/CUMEM cnode7-009:270315:280163 [7] NCCL INFO Channel 14/0 : 15[7] -> 8[0] via P2P/CUMEM cnode7-009:270315:280163 [7] NCCL INFO Channel 01/0 : 15[7] -> 14[6] via P2P/CUMEM cnode7-009:270315:280163 [7] NCCL INFO Channel 03/0 : 15[7] -> 14[6] via P2P/CUMEM cnode7-009:270315:280163 [7] NCCL INFO Channel 05/0 : 15[7] -> 14[6] via P2P/CUMEM cnode7-009:270308:279372 [0] NCCL INFO Channel 01/0 : 0[0] -> 8[0] [receive] via NET/IB/0/GDRDMA cnode7-009:270308:279372 [0] NCCL INFO Channel 09/0 : 0[0] -> 8[0] [receive] via NET/IB/0/GDRDMA cnode7-009:270308:279372 [0] NCCL INFO Channel 00/0 : 8[0] -> 0[0] [send] via NET/IB/0/GDRDMA cnode7-009:270308:279372 [0] NCCL INFO Channel 08/0 : 8[0] -> 0[0] [send] via NET/IB/0/GDRDMA cnode7-009:270311:279721 [3] NCCL INFO Channel 01/0 : 11[3] -> 10[2] via P2P/CUMEM cnode7-009:270311:279721 [3] NCCL INFO Channel 05/0 : 11[3] -> 10[2] via P2P/CUMEM cnode7-009:270311:279721 [3] NCCL INFO Channel 07/0 : 11[3] -> 10[2] via P2P/CUMEM cnode7-009:270311:279721 [3] NCCL INFO Channel 09/0 : 11[3] -> 10[2] via P2P/CUMEM cnode7-009:270311:279721 [3] NCCL INFO Channel 13/0 : 11[3] -> 10[2] via P2P/CUMEM cnode7-009:270311:279721 [3] NCCL INFO Channel 15/0 : 11[3] -> 10[2] via P2P/CUMEM cnode7-009:270312:279866 [4] NCCL INFO Channel 01/0 : 12[4] -> 11[3] via P2P/CUMEM cnode7-009:270312:279866 [4] NCCL INFO Channel 03/0 : 12[4] -> 11[3] via P2P/CUMEM cnode7-009:270312:279866 [4] NCCL INFO Channel 05/0 : 12[4] -> 11[3] via P2P/CUMEM cnode7-009:270312:279866 [4] NCCL INFO Channel 07/0 : 12[4] -> 11[3] via P2P/CUMEM cnode7-009:270312:279866 [4] NCCL INFO Channel 09/0 : 12[4] -> 11[3] via P2P/CUMEM cnode7-009:270312:279866 [4] NCCL INFO Channel 11/0 : 12[4] -> 11[3] via P2P/CUMEM cnode7-009:270312:279866 [4] NCCL INFO Channel 13/0 : 12[4] -> 11[3] via P2P/CUMEM cnode7-009:270312:279866 [4] NCCL INFO Channel 15/0 : 12[4] -> 11[3] via P2P/CUMEM cnode7-008:628125:637915 [2] NCCL INFO Channel 00/0 : 2[2] -> 1[1] via P2P/CUMEM cnode7-008:628125:637915 [2] NCCL INFO Channel 02/0 : 2[2] -> 1[1] via P2P/CUMEM cnode7-008:628125:637915 [2] NCCL INFO Channel 04/0 : 2[2] -> 1[1] via P2P/CUMEM cnode7-008:628125:637915 [2] NCCL INFO Channel 06/0 : 2[2] -> 1[1] via P2P/CUMEM cnode7-008:628125:637915 [2] NCCL INFO Channel 08/0 : 2[2] -> 1[1] via P2P/CUMEM cnode7-008:628125:637915 [2] NCCL INFO Channel 10/0 : 2[2] -> 1[1] via P2P/CUMEM cnode7-008:628125:637915 [2] NCCL INFO Channel 12/0 : 2[2] -> 1[1] via P2P/CUMEM cnode7-008:628125:637915 [2] NCCL INFO Channel 14/0 : 2[2] -> 1[1] via P2P/CUMEM cnode7-008:628127:637497 [4] NCCL INFO Channel 04/0 : 12[4] -> 4[4] [receive] via NET/IB/4/GDRDMA cnode7-008:628127:637497 [4] NCCL INFO Channel 12/0 : 12[4] -> 4[4] [receive] via NET/IB/4/GDRDMA cnode7-008:628127:637497 [4] NCCL INFO Channel 05/0 : 4[4] -> 12[4] [send] via NET/IB/4/GDRDMA cnode7-008:628127:637497 [4] NCCL INFO Channel 13/0 : 4[4] -> 12[4] [send] via NET/IB/4/GDRDMA cnode7-008:628127:637497 [4] NCCL INFO Channel 00/0 : 4[4] -> 3[3] via P2P/CUMEM cnode7-008:628127:637497 [4] NCCL INFO Channel 02/0 : 4[4] -> 3[3] via P2P/CUMEM cnode7-008:628127:637497 [4] NCCL INFO Channel 04/0 : 4[4] -> 3[3] via P2P/CUMEM cnode7-008:628127:637497 [4] NCCL INFO Channel 06/0 : 4[4] -> 3[3] via P2P/CUMEM cnode7-008:628127:637497 [4] NCCL INFO Channel 08/0 : 4[4] -> 3[3] via P2P/CUMEM cnode7-008:628127:637497 [4] NCCL INFO Channel 10/0 : 4[4] -> 3[3] via P2P/CUMEM cnode7-008:628127:637497 [4] NCCL INFO Channel 12/0 : 4[4] -> 3[3] via P2P/CUMEM cnode7-008:628127:637497 [4] NCCL INFO Channel 14/0 : 4[4] -> 3[3] via P2P/CUMEM cnode7-008:628130:637920 [7] NCCL INFO Channel 01/0 : 7[7] -> 0[0] via P2P/CUMEM cnode7-008:628130:637920 [7] NCCL INFO Channel 03/0 : 7[7] -> 0[0] via P2P/CUMEM cnode7-008:628130:637920 [7] NCCL INFO Channel 05/0 : 7[7] -> 0[0] via P2P/CUMEM cnode7-008:628130:637920 [7] NCCL INFO Channel 07/0 : 7[7] -> 0[0] via P2P/CUMEM cnode7-008:628130:637920 [7] NCCL INFO Channel 09/0 : 7[7] -> 0[0] via P2P/CUMEM cnode7-008:628130:637920 [7] NCCL INFO Channel 11/0 : 7[7] -> 0[0] via P2P/CUMEM cnode7-008:628130:637920 [7] NCCL INFO Channel 13/0 : 7[7] -> 0[0] via P2P/CUMEM cnode7-008:628130:637920 [7] NCCL INFO Channel 15/0 : 7[7] -> 0[0] via P2P/CUMEM cnode7-008:628130:637920 [7] NCCL INFO Channel 00/0 : 7[7] -> 6[6] via P2P/CUMEM cnode7-008:628130:637920 [7] NCCL INFO Channel 02/0 : 7[7] -> 6[6] via P2P/CUMEM cnode7-008:628130:637920 [7] NCCL INFO Channel 04/0 : 7[7] -> 6[6] via P2P/CUMEM cnode7-008:628130:637920 [7] NCCL INFO Channel 08/0 : 7[7] -> 6[6] via P2P/CUMEM cnode7-008:628130:637920 [7] NCCL INFO Channel 10/0 : 7[7] -> 6[6] via P2P/CUMEM cnode7-008:628130:637920 [7] NCCL INFO Channel 12/0 : 7[7] -> 6[6] via P2P/CUMEM cnode7-008:628124:637498 [1] NCCL INFO Channel 02/0 : 1[1] -> 0[0] via P2P/CUMEM cnode7-008:628124:637498 [1] NCCL INFO Channel 04/0 : 1[1] -> 0[0] via P2P/CUMEM cnode7-008:628124:637498 [1] NCCL INFO Channel 06/0 : 1[1] -> 0[0] via P2P/CUMEM cnode7-008:628124:637498 [1] NCCL INFO Channel 10/0 : 1[1] -> 0[0] via P2P/CUMEM cnode7-008:628124:637498 [1] NCCL INFO Channel 12/0 : 1[1] -> 0[0] via P2P/CUMEM cnode7-008:628124:637498 [1] NCCL INFO Channel 14/0 : 1[1] -> 0[0] via P2P/CUMEM cnode7-009:270313:279722 [5] NCCL INFO Channel 01/0 : 13[5] -> 12[4] via P2P/CUMEM cnode7-009:270313:279722 [5] NCCL INFO Channel 03/0 : 13[5] -> 12[4] via P2P/CUMEM cnode7-009:270313:279722 [5] NCCL INFO Channel 07/0 : 13[5] -> 12[4] via P2P/CUMEM cnode7-009:270313:279722 [5] NCCL INFO Channel 09/0 : 13[5] -> 12[4] via P2P/CUMEM cnode7-009:270313:279722 [5] NCCL INFO Channel 11/0 : 13[5] -> 12[4] via P2P/CUMEM cnode7-009:270313:279722 [5] NCCL INFO Channel 15/0 : 13[5] -> 12[4] via P2P/CUMEM cnode7-008:628128:637782 [5] NCCL INFO Channel 00/0 : 5[5] -> 4[4] via P2P/CUMEM cnode7-008:628128:637782 [5] NCCL INFO Channel 02/0 : 5[5] -> 4[4] via P2P/CUMEM cnode7-008:628128:637782 [5] NCCL INFO Channel 06/0 : 5[5] -> 4[4] via P2P/CUMEM cnode7-008:628128:637782 [5] NCCL INFO Channel 08/0 : 5[5] -> 4[4] via P2P/CUMEM cnode7-008:628128:637782 [5] NCCL INFO Channel 10/0 : 5[5] -> 4[4] via P2P/CUMEM cnode7-008:628128:637782 [5] NCCL INFO Channel 14/0 : 5[5] -> 4[4] via P2P/CUMEM cnode7-008:628129:637512 [6] NCCL INFO Channel 00/0 : 6[6] -> 5[5] via P2P/CUMEM cnode7-008:628129:637512 [6] NCCL INFO Channel 02/0 : 6[6] -> 5[5] via P2P/CUMEM cnode7-008:628129:637512 [6] NCCL INFO Channel 04/0 : 6[6] -> 5[5] via P2P/CUMEM cnode7-008:628129:637512 [6] NCCL INFO Channel 06/0 : 6[6] -> 5[5] via P2P/CUMEM cnode7-008:628129:637512 [6] NCCL INFO Channel 08/0 : 6[6] -> 5[5] via P2P/CUMEM cnode7-008:628129:637512 [6] NCCL INFO Channel 10/0 : 6[6] -> 5[5] via P2P/CUMEM cnode7-008:628129:637512 [6] NCCL INFO Channel 12/0 : 6[6] -> 5[5] via P2P/CUMEM cnode7-008:628129:637512 [6] NCCL INFO Channel 14/0 : 6[6] -> 5[5] via P2P/CUMEM cnode7-009:270314:279443 [6] NCCL INFO Channel 09/0 : 14[6] -> 13[5] via P2P/CUMEM cnode7-009:270314:279443 [6] NCCL INFO Channel 11/0 : 14[6] -> 13[5] via P2P/CUMEM cnode7-009:270314:279443 [6] NCCL INFO Channel 13/0 : 14[6] -> 13[5] via P2P/CUMEM cnode7-009:270314:279443 [6] NCCL INFO Channel 15/0 : 14[6] -> 13[5] via P2P/CUMEM cnode7-009:270315:280163 [7] NCCL INFO Channel 09/0 : 15[7] -> 14[6] via P2P/CUMEM cnode7-009:270315:280163 [7] NCCL INFO Channel 11/0 : 15[7] -> 14[6] via P2P/CUMEM cnode7-009:270315:280163 [7] NCCL INFO Channel 13/0 : 15[7] -> 14[6] via P2P/CUMEM cnode7-008:628125:637915 [2] NCCL INFO Connected all rings cnode7-008:628125:637915 [2] NCCL INFO Channel 00/0 : 2[2] -> 3[3] via P2P/CUMEM cnode7-008:628127:637497 [4] NCCL INFO Connected all rings cnode7-008:628130:637920 [7] NCCL INFO Connected all rings cnode7-008:628124:637498 [1] NCCL INFO Connected all rings cnode7-008:628124:637498 [1] NCCL INFO Channel 00/0 : 1[1] -> 2[2] via P2P/CUMEM cnode7-008:628124:637498 [1] NCCL INFO Channel 04/0 : 1[1] -> 2[2] via P2P/CUMEM cnode7-008:628124:637498 [1] NCCL INFO Channel 06/0 : 1[1] -> 2[2] via P2P/CUMEM cnode7-008:628124:637498 [1] NCCL INFO Channel 08/0 : 1[1] -> 2[2] via P2P/CUMEM cnode7-008:628124:637498 [1] NCCL INFO Channel 12/0 : 1[1] -> 2[2] via P2P/CUMEM cnode7-008:628124:637498 [1] NCCL INFO Channel 14/0 : 1[1] -> 2[2] via P2P/CUMEM cnode7-008:628124:637498 [1] NCCL INFO Channel 01/0 : 1[1] -> 9[1] [send] via NET/IB/1/GDRDMA cnode7-008:628124:637498 [1] NCCL INFO Channel 09/0 : 1[1] -> 9[1] [send] via NET/IB/1/GDRDMA cnode7-009:270310:279373 [2] NCCL INFO Connected all rings cnode7-009:270310:279373 [2] NCCL INFO Channel 01/0 : 10[2] -> 11[3] via P2P/CUMEM cnode7-009:270310:279373 [2] NCCL INFO Channel 02/0 : 10[2] -> 11[3] via P2P/CUMEM cnode7-009:270310:279373 [2] NCCL INFO Channel 05/0 : 10[2] -> 11[3] via P2P/CUMEM cnode7-009:270310:279373 [2] NCCL INFO Channel 07/0 : 10[2] -> 11[3] via P2P/CUMEM cnode7-009:270310:279373 [2] NCCL INFO Channel 09/0 : 10[2] -> 11[3] via P2P/CUMEM cnode7-009:270310:279373 [2] NCCL INFO Channel 10/0 : 10[2] -> 11[3] via P2P/CUMEM cnode7-009:270310:279373 [2] NCCL INFO Channel 13/0 : 10[2] -> 11[3] via P2P/CUMEM cnode7-009:270310:279373 [2] NCCL INFO Channel 15/0 : 10[2] -> 11[3] via P2P/CUMEM cnode7-009:270310:279373 [2] NCCL INFO Channel 02/0 : 2[2] -> 10[2] [receive] via NET/IB/2/GDRDMA cnode7-009:270310:279373 [2] NCCL INFO Channel 10/0 : 2[2] -> 10[2] [receive] via NET/IB/2/GDRDMA cnode7-009:270310:279373 [2] NCCL INFO Channel 00/0 : 10[2] -> 9[1] via P2P/CUMEM cnode7-009:270310:279373 [2] NCCL INFO Channel 04/0 : 10[2] -> 9[1] via P2P/CUMEM cnode7-009:270310:279373 [2] NCCL INFO Channel 06/0 : 10[2] -> 9[1] via P2P/CUMEM cnode7-009:270310:279373 [2] NCCL INFO Channel 08/0 : 10[2] -> 9[1] via P2P/CUMEM cnode7-009:270310:279373 [2] NCCL INFO Channel 12/0 : 10[2] -> 9[1] via P2P/CUMEM cnode7-009:270310:279373 [2] NCCL INFO Channel 14/0 : 10[2] -> 9[1] via P2P/CUMEM cnode7-009:270313:279722 [5] NCCL INFO Connected all rings cnode7-009:270313:279722 [5] NCCL INFO Channel 01/0 : 13[5] -> 14[6] via P2P/CUMEM cnode7-009:270313:279722 [5] NCCL INFO Channel 03/0 : 13[5] -> 14[6] via P2P/CUMEM cnode7-009:270313:279722 [5] NCCL INFO Channel 05/0 : 13[5] -> 14[6] via P2P/CUMEM cnode7-009:270313:279722 [5] NCCL INFO Channel 07/0 : 13[5] -> 14[6] via P2P/CUMEM cnode7-009:270313:279722 [5] NCCL INFO Channel 09/0 : 13[5] -> 14[6] via P2P/CUMEM cnode7-009:270313:279722 [5] NCCL INFO Channel 11/0 : 13[5] -> 14[6] via P2P/CUMEM cnode7-009:270313:279722 [5] NCCL INFO Channel 13/0 : 13[5] -> 14[6] via P2P/CUMEM cnode7-009:270313:279722 [5] NCCL INFO Channel 15/0 : 13[5] -> 14[6] via P2P/CUMEM cnode7-009:270313:279722 [5] NCCL INFO Channel 05/0 : 5[5] -> 13[5] [receive] via NET/IB/6/GDRDMA cnode7-009:270313:279722 [5] NCCL INFO Channel 13/0 : 5[5] -> 13[5] [receive] via NET/IB/6/GDRDMA cnode7-009:270313:279722 [5] NCCL INFO Channel 00/0 : 13[5] -> 12[4] via P2P/CUMEM cnode7-009:270313:279722 [5] NCCL INFO Channel 02/0 : 13[5] -> 12[4] via P2P/CUMEM cnode7-009:270313:279722 [5] NCCL INFO Channel 04/0 : 13[5] -> 12[4] via P2P/CUMEM cnode7-009:270313:279722 [5] NCCL INFO Channel 06/0 : 13[5] -> 12[4] via P2P/CUMEM cnode7-009:270313:279722 [5] NCCL INFO Channel 08/0 : 13[5] -> 12[4] via P2P/CUMEM cnode7-009:270313:279722 [5] NCCL INFO Channel 10/0 : 13[5] -> 12[4] via P2P/CUMEM cnode7-009:270313:279722 [5] NCCL INFO Channel 12/0 : 13[5] -> 12[4] via P2P/CUMEM cnode7-009:270313:279722 [5] NCCL INFO Channel 14/0 : 13[5] -> 12[4] via P2P/CUMEM cnode7-008:628128:637782 [5] NCCL INFO Connected all rings cnode7-008:628128:637782 [5] NCCL INFO Channel 00/0 : 5[5] -> 6[6] via P2P/CUMEM cnode7-008:628128:637782 [5] NCCL INFO Channel 02/0 : 5[5] -> 6[6] via P2P/CUMEM cnode7-008:628128:637782 [5] NCCL INFO Channel 04/0 : 5[5] -> 6[6] via P2P/CUMEM cnode7-008:628128:637782 [5] NCCL INFO Channel 08/0 : 5[5] -> 6[6] via P2P/CUMEM cnode7-008:628128:637782 [5] NCCL INFO Channel 10/0 : 5[5] -> 6[6] via P2P/CUMEM cnode7-008:628128:637782 [5] NCCL INFO Channel 12/0 : 5[5] -> 6[6] via P2P/CUMEM cnode7-008:628128:637782 [5] NCCL INFO Channel 05/0 : 5[5] -> 13[5] [send] via NET/IB/6/GDRDMA cnode7-008:628128:637782 [5] NCCL INFO Channel 13/0 : 5[5] -> 13[5] [send] via NET/IB/6/GDRDMA cnode7-008:628128:637782 [5] NCCL INFO Channel 01/0 : 5[5] -> 4[4] via P2P/CUMEM cnode7-008:628128:637782 [5] NCCL INFO Channel 03/0 : 5[5] -> 4[4] via P2P/CUMEM cnode7-008:628128:637782 [5] NCCL INFO Channel 04/0 : 5[5] -> 4[4] via P2P/CUMEM cnode7-008:628128:637782 [5] NCCL INFO Channel 07/0 : 5[5] -> 4[4] via P2P/CUMEM cnode7-008:628128:637782 [5] NCCL INFO Channel 09/0 : 5[5] -> 4[4] via P2P/CUMEM cnode7-008:628128:637782 [5] NCCL INFO Channel 11/0 : 5[5] -> 4[4] via P2P/CUMEM cnode7-008:628128:637782 [5] NCCL INFO Channel 12/0 : 5[5] -> 4[4] via P2P/CUMEM cnode7-008:628128:637782 [5] NCCL INFO Channel 15/0 : 5[5] -> 4[4] via P2P/CUMEM cnode7-008:628129:637512 [6] NCCL INFO Connected all rings cnode7-008:628129:637512 [6] NCCL INFO Channel 00/0 : 6[6] -> 7[7] via P2P/CUMEM cnode7-008:628129:637512 [6] NCCL INFO Channel 02/0 : 6[6] -> 7[7] via P2P/CUMEM cnode7-008:628129:637512 [6] NCCL INFO Channel 04/0 : 6[6] -> 7[7] via P2P/CUMEM cnode7-008:628129:637512 [6] NCCL INFO Channel 06/0 : 6[6] -> 7[7] via P2P/CUMEM cnode7-008:628129:637512 [6] NCCL INFO Channel 08/0 : 6[6] -> 7[7] via P2P/CUMEM cnode7-008:628129:637512 [6] NCCL INFO Channel 10/0 : 6[6] -> 7[7] via P2P/CUMEM cnode7-008:628129:637512 [6] NCCL INFO Channel 12/0 : 6[6] -> 7[7] via P2P/CUMEM cnode7-008:628129:637512 [6] NCCL INFO Channel 14/0 : 6[6] -> 7[7] via P2P/CUMEM cnode7-008:628129:637512 [6] NCCL INFO Channel 06/0 : 6[6] -> 14[6] [send] via NET/IB/7/GDRDMA cnode7-008:628129:637512 [6] NCCL INFO Channel 14/0 : 6[6] -> 14[6] [send] via NET/IB/7/GDRDMA cnode7-008:628129:637512 [6] NCCL INFO Channel 01/0 : 6[6] -> 5[5] via P2P/CUMEM cnode7-008:628129:637512 [6] NCCL INFO Channel 03/0 : 6[6] -> 5[5] via P2P/CUMEM cnode7-008:628129:637512 [6] NCCL INFO Channel 05/0 : 6[6] -> 5[5] via P2P/CUMEM cnode7-008:628129:637512 [6] NCCL INFO Channel 07/0 : 6[6] -> 5[5] via P2P/CUMEM cnode7-008:628129:637512 [6] NCCL INFO Channel 09/0 : 6[6] -> 5[5] via P2P/CUMEM cnode7-008:628129:637512 [6] NCCL INFO Channel 11/0 : 6[6] -> 5[5] via P2P/CUMEM cnode7-008:628129:637512 [6] NCCL INFO Channel 13/0 : 6[6] -> 5[5] via P2P/CUMEM cnode7-008:628129:637512 [6] NCCL INFO Channel 15/0 : 6[6] -> 5[5] via P2P/CUMEM cnode7-008:628126:637787 [3] NCCL INFO Connected all rings cnode7-008:628126:637787 [3] NCCL INFO Channel 00/0 : 3[3] -> 4[4] via P2P/CUMEM cnode7-008:628126:637787 [3] NCCL INFO Channel 02/0 : 3[3] -> 4[4] via P2P/CUMEM cnode7-008:628126:637787 [3] NCCL INFO Channel 06/0 : 3[3] -> 4[4] via P2P/CUMEM cnode7-008:628126:637787 [3] NCCL INFO Channel 08/0 : 3[3] -> 4[4] via P2P/CUMEM cnode7-008:628126:637787 [3] NCCL INFO Channel 10/0 : 3[3] -> 4[4] via P2P/CUMEM cnode7-008:628126:637787 [3] NCCL INFO Channel 14/0 : 3[3] -> 4[4] via P2P/CUMEM cnode7-008:628126:637787 [3] NCCL INFO Channel 03/0 : 3[3] -> 11[3] [send] via NET/IB/3/GDRDMA cnode7-008:628126:637787 [3] NCCL INFO Channel 11/0 : 3[3] -> 11[3] [send] via NET/IB/3/GDRDMA cnode7-008:628126:637787 [3] NCCL INFO Channel 01/0 : 3[3] -> 2[2] via P2P/CUMEM cnode7-008:628126:637787 [3] NCCL INFO Channel 02/0 : 3[3] -> 2[2] via P2P/CUMEM cnode7-008:628126:637787 [3] NCCL INFO Channel 05/0 : 3[3] -> 2[2] via P2P/CUMEM cnode7-008:628126:637787 [3] NCCL INFO Channel 07/0 : 3[3] -> 2[2] via P2P/CUMEM cnode7-008:628126:637787 [3] NCCL INFO Channel 09/0 : 3[3] -> 2[2] via P2P/CUMEM cnode7-008:628126:637787 [3] NCCL INFO Channel 10/0 : 3[3] -> 2[2] via P2P/CUMEM cnode7-008:628126:637787 [3] NCCL INFO Channel 13/0 : 3[3] -> 2[2] via P2P/CUMEM cnode7-008:628126:637787 [3] NCCL INFO Channel 15/0 : 3[3] -> 2[2] via P2P/CUMEM cnode7-009:270314:279443 [6] NCCL INFO Connected all rings cnode7-009:270314:279443 [6] NCCL INFO Channel 01/0 : 14[6] -> 15[7] via P2P/CUMEM cnode7-009:270314:279443 [6] NCCL INFO Channel 03/0 : 14[6] -> 15[7] via P2P/CUMEM cnode7-009:270314:279443 [6] NCCL INFO Channel 05/0 : 14[6] -> 15[7] via P2P/CUMEM cnode7-009:270314:279443 [6] NCCL INFO Channel 06/0 : 14[6] -> 15[7] via P2P/CUMEM cnode7-009:270314:279443 [6] NCCL INFO Channel 09/0 : 14[6] -> 15[7] via P2P/CUMEM cnode7-009:270314:279443 [6] NCCL INFO Channel 11/0 : 14[6] -> 15[7] via P2P/CUMEM cnode7-009:270314:279443 [6] NCCL INFO Channel 13/0 : 14[6] -> 15[7] via P2P/CUMEM cnode7-009:270314:279443 [6] NCCL INFO Channel 14/0 : 14[6] -> 15[7] via P2P/CUMEM cnode7-009:270314:279443 [6] NCCL INFO Channel 06/0 : 6[6] -> 14[6] [receive] via NET/IB/7/GDRDMA cnode7-009:270314:279443 [6] NCCL INFO Channel 14/0 : 6[6] -> 14[6] [receive] via NET/IB/7/GDRDMA cnode7-009:270314:279443 [6] NCCL INFO Channel 00/0 : 14[6] -> 13[5] via P2P/CUMEM cnode7-009:270314:279443 [6] NCCL INFO Channel 02/0 : 14[6] -> 13[5] via P2P/CUMEM cnode7-009:270314:279443 [6] NCCL INFO Channel 04/0 : 14[6] -> 13[5] via P2P/CUMEM cnode7-009:270314:279443 [6] NCCL INFO Channel 08/0 : 14[6] -> 13[5] via P2P/CUMEM cnode7-009:270314:279443 [6] NCCL INFO Channel 10/0 : 14[6] -> 13[5] via P2P/CUMEM cnode7-009:270314:279443 [6] NCCL INFO Channel 12/0 : 14[6] -> 13[5] via P2P/CUMEM cnode7-009:270315:280163 [7] NCCL INFO Connected all rings cnode7-009:270315:280163 [7] NCCL INFO Channel 07/0 : 7[7] -> 15[7] [receive] via NET/IB/8/GDRDMA cnode7-009:270315:280163 [7] NCCL INFO Channel 15/0 : 7[7] -> 15[7] [receive] via NET/IB/8/GDRDMA cnode7-009:270315:280163 [7] NCCL INFO Channel 01/0 : 15[7] -> 8[0] via P2P/CUMEM cnode7-009:270315:280163 [7] NCCL INFO Channel 03/0 : 15[7] -> 8[0] via P2P/CUMEM cnode7-009:270315:280163 [7] NCCL INFO Channel 05/0 : 15[7] -> 8[0] via P2P/CUMEM cnode7-009:270315:280163 [7] NCCL INFO Channel 07/0 : 15[7] -> 8[0] via P2P/CUMEM cnode7-009:270315:280163 [7] NCCL INFO Channel 09/0 : 15[7] -> 8[0] via P2P/CUMEM cnode7-009:270315:280163 [7] NCCL INFO Channel 11/0 : 15[7] -> 8[0] via P2P/CUMEM cnode7-009:270315:280163 [7] NCCL INFO Channel 13/0 : 15[7] -> 8[0] via P2P/CUMEM cnode7-009:270315:280163 [7] NCCL INFO Channel 15/0 : 15[7] -> 8[0] via P2P/CUMEM cnode7-009:270315:280163 [7] NCCL INFO Channel 00/0 : 15[7] -> 14[6] via P2P/CUMEM cnode7-009:270315:280163 [7] NCCL INFO Channel 02/0 : 15[7] -> 14[6] via P2P/CUMEM cnode7-009:270315:280163 [7] NCCL INFO Channel 04/0 : 15[7] -> 14[6] via P2P/CUMEM cnode7-009:270315:280163 [7] NCCL INFO Channel 06/0 : 15[7] -> 14[6] via P2P/CUMEM cnode7-009:270315:280163 [7] NCCL INFO Channel 08/0 : 15[7] -> 14[6] via P2P/CUMEM cnode7-009:270315:280163 [7] NCCL INFO Channel 10/0 : 15[7] -> 14[6] via P2P/CUMEM cnode7-009:270315:280163 [7] NCCL INFO Channel 12/0 : 15[7] -> 14[6] via P2P/CUMEM cnode7-009:270315:280163 [7] NCCL INFO Channel 14/0 : 15[7] -> 14[6] via P2P/CUMEM cnode7-009:270308:279372 [0] NCCL INFO Connected all rings cnode7-009:270308:279372 [0] NCCL INFO Channel 00/0 : 8[0] -> 9[1] via P2P/CUMEM cnode7-009:270308:279372 [0] NCCL INFO Channel 03/0 : 8[0] -> 9[1] via P2P/CUMEM cnode7-009:270308:279372 [0] NCCL INFO Channel 05/0 : 8[0] -> 9[1] via P2P/CUMEM cnode7-009:270308:279372 [0] NCCL INFO Channel 07/0 : 8[0] -> 9[1] via P2P/CUMEM cnode7-009:270308:279372 [0] NCCL INFO Channel 08/0 : 8[0] -> 9[1] via P2P/CUMEM cnode7-009:270308:279372 [0] NCCL INFO Channel 11/0 : 8[0] -> 9[1] via P2P/CUMEM cnode7-009:270308:279372 [0] NCCL INFO Channel 13/0 : 8[0] -> 9[1] via P2P/CUMEM cnode7-009:270308:279372 [0] NCCL INFO Channel 15/0 : 8[0] -> 9[1] via P2P/CUMEM cnode7-009:270308:279372 [0] NCCL INFO Channel 02/0 : 8[0] -> 15[7] via P2P/CUMEM cnode7-009:270308:279372 [0] NCCL INFO Channel 04/0 : 8[0] -> 15[7] via P2P/CUMEM cnode7-009:270308:279372 [0] NCCL INFO Channel 06/0 : 8[0] -> 15[7] via P2P/CUMEM cnode7-009:270308:279372 [0] NCCL INFO Channel 10/0 : 8[0] -> 15[7] via P2P/CUMEM cnode7-009:270308:279372 [0] NCCL INFO Channel 12/0 : 8[0] -> 15[7] via P2P/CUMEM cnode7-009:270308:279372 [0] NCCL INFO Channel 14/0 : 8[0] -> 15[7] via P2P/CUMEM cnode7-009:270308:279372 [0] NCCL INFO Channel 00/0 : 0[0] -> 8[0] [receive] via NET/IB/0/GDRDMA cnode7-009:270308:279372 [0] NCCL INFO Channel 08/0 : 0[0] -> 8[0] [receive] via NET/IB/0/GDRDMA cnode7-009:270311:279721 [3] NCCL INFO Connected all rings cnode7-009:270311:279721 [3] NCCL INFO Channel 01/0 : 11[3] -> 12[4] via P2P/CUMEM cnode7-009:270311:279721 [3] NCCL INFO Channel 03/0 : 11[3] -> 12[4] via P2P/CUMEM cnode7-009:270311:279721 [3] NCCL INFO Channel 05/0 : 11[3] -> 12[4] via P2P/CUMEM cnode7-009:270311:279721 [3] NCCL INFO Channel 07/0 : 11[3] -> 12[4] via P2P/CUMEM cnode7-009:270311:279721 [3] NCCL INFO Channel 09/0 : 11[3] -> 12[4] via P2P/CUMEM cnode7-009:270311:279721 [3] NCCL INFO Channel 11/0 : 11[3] -> 12[4] via P2P/CUMEM cnode7-009:270311:279721 [3] NCCL INFO Channel 13/0 : 11[3] -> 12[4] via P2P/CUMEM cnode7-009:270311:279721 [3] NCCL INFO Channel 15/0 : 11[3] -> 12[4] via P2P/CUMEM cnode7-009:270311:279721 [3] NCCL INFO Channel 03/0 : 3[3] -> 11[3] [receive] via NET/IB/3/GDRDMA cnode7-009:270311:279721 [3] NCCL INFO Channel 11/0 : 3[3] -> 11[3] [receive] via NET/IB/3/GDRDMA cnode7-009:270311:279721 [3] NCCL INFO Channel 00/0 : 11[3] -> 10[2] via P2P/CUMEM cnode7-009:270311:279721 [3] NCCL INFO Channel 02/0 : 11[3] -> 10[2] via P2P/CUMEM cnode7-009:270311:279721 [3] NCCL INFO Channel 04/0 : 11[3] -> 10[2] via P2P/CUMEM cnode7-009:270311:279721 [3] NCCL INFO Channel 06/0 : 11[3] -> 10[2] via P2P/CUMEM cnode7-009:270311:279721 [3] NCCL INFO Channel 08/0 : 11[3] -> 10[2] via P2P/CUMEM cnode7-009:270311:279721 [3] NCCL INFO Channel 10/0 : 11[3] -> 10[2] via P2P/CUMEM cnode7-009:270311:279721 [3] NCCL INFO Channel 12/0 : 11[3] -> 10[2] via P2P/CUMEM cnode7-009:270311:279721 [3] NCCL INFO Channel 14/0 : 11[3] -> 10[2] via P2P/CUMEM cnode7-009:270312:279866 [4] NCCL INFO Connected all rings cnode7-009:270312:279866 [4] NCCL INFO Channel 01/0 : 12[4] -> 13[5] via P2P/CUMEM cnode7-009:270312:279866 [4] NCCL INFO Channel 03/0 : 12[4] -> 13[5] via P2P/CUMEM cnode7-009:270312:279866 [4] NCCL INFO Channel 04/0 : 12[4] -> 13[5] via P2P/CUMEM cnode7-009:270312:279866 [4] NCCL INFO Channel 07/0 : 12[4] -> 13[5] via P2P/CUMEM cnode7-009:270312:279866 [4] NCCL INFO Channel 09/0 : 12[4] -> 13[5] via P2P/CUMEM cnode7-009:270312:279866 [4] NCCL INFO Channel 11/0 : 12[4] -> 13[5] via P2P/CUMEM cnode7-009:270312:279866 [4] NCCL INFO Channel 12/0 : 12[4] -> 13[5] via P2P/CUMEM cnode7-009:270312:279866 [4] NCCL INFO Channel 15/0 : 12[4] -> 13[5] via P2P/CUMEM cnode7-009:270312:279866 [4] NCCL INFO Channel 04/0 : 4[4] -> 12[4] [receive] via NET/IB/4/GDRDMA cnode7-009:270312:279866 [4] NCCL INFO Channel 12/0 : 4[4] -> 12[4] [receive] via NET/IB/4/GDRDMA cnode7-009:270312:279866 [4] NCCL INFO Channel 00/0 : 12[4] -> 11[3] via P2P/CUMEM cnode7-009:270312:279866 [4] NCCL INFO Channel 02/0 : 12[4] -> 11[3] via P2P/CUMEM cnode7-009:270312:279866 [4] NCCL INFO Channel 06/0 : 12[4] -> 11[3] via P2P/CUMEM cnode7-009:270312:279866 [4] NCCL INFO Channel 08/0 : 12[4] -> 11[3] via P2P/CUMEM cnode7-009:270312:279866 [4] NCCL INFO Channel 10/0 : 12[4] -> 11[3] via P2P/CUMEM cnode7-009:270312:279866 [4] NCCL INFO Channel 14/0 : 12[4] -> 11[3] via P2P/CUMEM cnode7-009:270309:280008 [1] NCCL INFO Connected all rings cnode7-009:270309:280008 [1] NCCL INFO Channel 01/0 : 9[1] -> 10[2] via P2P/CUMEM cnode7-009:270309:280008 [1] NCCL INFO Channel 03/0 : 9[1] -> 10[2] via P2P/CUMEM cnode7-009:270309:280008 [1] NCCL INFO Channel 05/0 : 9[1] -> 10[2] via P2P/CUMEM cnode7-009:270309:280008 [1] NCCL INFO Channel 07/0 : 9[1] -> 10[2] via P2P/CUMEM cnode7-009:270309:280008 [1] NCCL INFO Channel 09/0 : 9[1] -> 10[2] via P2P/CUMEM cnode7-009:270309:280008 [1] NCCL INFO Channel 11/0 : 9[1] -> 10[2] via P2P/CUMEM cnode7-009:270309:280008 [1] NCCL INFO Channel 13/0 : 9[1] -> 10[2] via P2P/CUMEM cnode7-009:270309:280008 [1] NCCL INFO Channel 15/0 : 9[1] -> 10[2] via P2P/CUMEM cnode7-009:270309:280008 [1] NCCL INFO Channel 01/0 : 1[1] -> 9[1] [receive] via NET/IB/1/GDRDMA cnode7-009:270309:280008 [1] NCCL INFO Channel 09/0 : 1[1] -> 9[1] [receive] via NET/IB/1/GDRDMA cnode7-009:270309:280008 [1] NCCL INFO Channel 00/0 : 9[1] -> 8[0] via P2P/CUMEM cnode7-009:270309:280008 [1] NCCL INFO Channel 02/0 : 9[1] -> 8[0] via P2P/CUMEM cnode7-009:270309:280008 [1] NCCL INFO Channel 04/0 : 9[1] -> 8[0] via P2P/CUMEM cnode7-009:270309:280008 [1] NCCL INFO Channel 06/0 : 9[1] -> 8[0] via P2P/CUMEM cnode7-009:270309:280008 [1] NCCL INFO Channel 08/0 : 9[1] -> 8[0] via P2P/CUMEM cnode7-009:270309:280008 [1] NCCL INFO Channel 10/0 : 9[1] -> 8[0] via P2P/CUMEM cnode7-009:270309:280008 [1] NCCL INFO Channel 12/0 : 9[1] -> 8[0] via P2P/CUMEM cnode7-009:270309:280008 [1] NCCL INFO Channel 14/0 : 9[1] -> 8[0] via P2P/CUMEM cnode7-008:628125:637915 [2] NCCL INFO Channel 02/0 : 2[2] -> 3[3] via P2P/CUMEM cnode7-008:628125:637915 [2] NCCL INFO Channel 04/0 : 2[2] -> 3[3] via P2P/CUMEM cnode7-008:628125:637915 [2] NCCL INFO Channel 06/0 : 2[2] -> 3[3] via P2P/CUMEM cnode7-008:628125:637915 [2] NCCL INFO Channel 08/0 : 2[2] -> 3[3] via P2P/CUMEM cnode7-008:628125:637915 [2] NCCL INFO Channel 10/0 : 2[2] -> 3[3] via P2P/CUMEM cnode7-008:628125:637915 [2] NCCL INFO Channel 12/0 : 2[2] -> 3[3] via P2P/CUMEM cnode7-008:628125:637915 [2] NCCL INFO Channel 14/0 : 2[2] -> 3[3] via P2P/CUMEM cnode7-008:628125:637915 [2] NCCL INFO Channel 02/0 : 2[2] -> 10[2] [send] via NET/IB/2/GDRDMA cnode7-008:628125:637915 [2] NCCL INFO Channel 10/0 : 2[2] -> 10[2] [send] via NET/IB/2/GDRDMA cnode7-008:628125:637915 [2] NCCL INFO Channel 01/0 : 2[2] -> 1[1] via P2P/CUMEM cnode7-008:628125:637915 [2] NCCL INFO Channel 03/0 : 2[2] -> 1[1] via P2P/CUMEM cnode7-008:628125:637915 [2] NCCL INFO Channel 05/0 : 2[2] -> 1[1] via P2P/CUMEM cnode7-008:628125:637915 [2] NCCL INFO Channel 07/0 : 2[2] -> 1[1] via P2P/CUMEM cnode7-008:628125:637915 [2] NCCL INFO Channel 09/0 : 2[2] -> 1[1] via P2P/CUMEM cnode7-008:628125:637915 [2] NCCL INFO Channel 11/0 : 2[2] -> 1[1] via P2P/CUMEM cnode7-008:628125:637915 [2] NCCL INFO Channel 13/0 : 2[2] -> 1[1] via P2P/CUMEM cnode7-008:628125:637915 [2] NCCL INFO Channel 15/0 : 2[2] -> 1[1] via P2P/CUMEM cnode7-008:628123:637496 [0] NCCL INFO Connected all rings cnode7-008:628123:637496 [0] NCCL INFO Channel 00/0 : 0[0] -> 1[1] via P2P/CUMEM cnode7-008:628123:637496 [0] NCCL INFO Channel 02/0 : 0[0] -> 1[1] via P2P/CUMEM cnode7-008:628123:637496 [0] NCCL INFO Channel 04/0 : 0[0] -> 1[1] via P2P/CUMEM cnode7-008:628123:637496 [0] NCCL INFO Channel 06/0 : 0[0] -> 1[1] via P2P/CUMEM cnode7-008:628123:637496 [0] NCCL INFO Channel 08/0 : 0[0] -> 1[1] via P2P/CUMEM cnode7-008:628123:637496 [0] NCCL INFO Channel 10/0 : 0[0] -> 1[1] via P2P/CUMEM cnode7-008:628123:637496 [0] NCCL INFO Channel 12/0 : 0[0] -> 1[1] via P2P/CUMEM cnode7-008:628123:637496 [0] NCCL INFO Channel 14/0 : 0[0] -> 1[1] via P2P/CUMEM cnode7-008:628123:637496 [0] NCCL INFO Channel 01/0 : 0[0] -> 7[7] via P2P/CUMEM cnode7-008:628123:637496 [0] NCCL INFO Channel 03/0 : 0[0] -> 7[7] via P2P/CUMEM cnode7-008:628123:637496 [0] NCCL INFO Channel 05/0 : 0[0] -> 7[7] via P2P/CUMEM cnode7-008:628123:637496 [0] NCCL INFO Channel 07/0 : 0[0] -> 7[7] via P2P/CUMEM cnode7-008:628123:637496 [0] NCCL INFO Channel 09/0 : 0[0] -> 7[7] via P2P/CUMEM cnode7-008:628123:637496 [0] NCCL INFO Channel 11/0 : 0[0] -> 7[7] via P2P/CUMEM cnode7-008:628123:637496 [0] NCCL INFO Channel 13/0 : 0[0] -> 7[7] via P2P/CUMEM cnode7-008:628123:637496 [0] NCCL INFO Channel 15/0 : 0[0] -> 7[7] via P2P/CUMEM cnode7-008:628123:637496 [0] NCCL INFO Channel 00/0 : 0[0] -> 8[0] [send] via NET/IB/0/GDRDMA cnode7-008:628123:637496 [0] NCCL INFO Channel 08/0 : 0[0] -> 8[0] [send] via NET/IB/0/GDRDMA cnode7-008:628127:637497 [4] NCCL INFO Channel 00/0 : 4[4] -> 5[5] via P2P/CUMEM cnode7-008:628127:637497 [4] NCCL INFO Channel 02/0 : 4[4] -> 5[5] via P2P/CUMEM cnode7-008:628127:637497 [4] NCCL INFO Channel 04/0 : 4[4] -> 5[5] via P2P/CUMEM cnode7-008:628127:637497 [4] NCCL INFO Channel 06/0 : 4[4] -> 5[5] via P2P/CUMEM cnode7-008:628127:637497 [4] NCCL INFO Channel 08/0 : 4[4] -> 5[5] via P2P/CUMEM cnode7-008:628127:637497 [4] NCCL INFO Channel 10/0 : 4[4] -> 5[5] via P2P/CUMEM cnode7-008:628127:637497 [4] NCCL INFO Channel 12/0 : 4[4] -> 5[5] via P2P/CUMEM cnode7-008:628127:637497 [4] NCCL INFO Channel 14/0 : 4[4] -> 5[5] via P2P/CUMEM cnode7-008:628127:637497 [4] NCCL INFO Channel 04/0 : 4[4] -> 12[4] [send] via NET/IB/4/GDRDMA cnode7-008:628127:637497 [4] NCCL INFO Channel 12/0 : 4[4] -> 12[4] [send] via NET/IB/4/GDRDMA cnode7-008:628127:637497 [4] NCCL INFO Channel 01/0 : 4[4] -> 3[3] via P2P/CUMEM cnode7-008:628127:637497 [4] NCCL INFO Channel 03/0 : 4[4] -> 3[3] via P2P/CUMEM cnode7-008:628127:637497 [4] NCCL INFO Channel 05/0 : 4[4] -> 3[3] via P2P/CUMEM cnode7-008:628127:637497 [4] NCCL INFO Channel 07/0 : 4[4] -> 3[3] via P2P/CUMEM cnode7-008:628127:637497 [4] NCCL INFO Channel 09/0 : 4[4] -> 3[3] via P2P/CUMEM cnode7-008:628127:637497 [4] NCCL INFO Channel 11/0 : 4[4] -> 3[3] via P2P/CUMEM cnode7-008:628127:637497 [4] NCCL INFO Channel 13/0 : 4[4] -> 3[3] via P2P/CUMEM cnode7-008:628127:637497 [4] NCCL INFO Channel 15/0 : 4[4] -> 3[3] via P2P/CUMEM cnode7-008:628130:637920 [7] NCCL INFO Channel 07/0 : 7[7] -> 15[7] [send] via NET/IB/8/GDRDMA cnode7-008:628130:637920 [7] NCCL INFO Channel 15/0 : 7[7] -> 15[7] [send] via NET/IB/8/GDRDMA cnode7-008:628130:637920 [7] NCCL INFO Channel 02/0 : 7[7] -> 0[0] via P2P/CUMEM cnode7-008:628130:637920 [7] NCCL INFO Channel 04/0 : 7[7] -> 0[0] via P2P/CUMEM cnode7-008:628130:637920 [7] NCCL INFO Channel 06/0 : 7[7] -> 0[0] via P2P/CUMEM cnode7-008:628130:637920 [7] NCCL INFO Channel 10/0 : 7[7] -> 0[0] via P2P/CUMEM cnode7-008:628130:637920 [7] NCCL INFO Channel 12/0 : 7[7] -> 0[0] via P2P/CUMEM cnode7-008:628130:637920 [7] NCCL INFO Channel 14/0 : 7[7] -> 0[0] via P2P/CUMEM cnode7-008:628130:637920 [7] NCCL INFO Channel 01/0 : 7[7] -> 6[6] via P2P/CUMEM cnode7-008:628130:637920 [7] NCCL INFO Channel 03/0 : 7[7] -> 6[6] via P2P/CUMEM cnode7-008:628130:637920 [7] NCCL INFO Channel 05/0 : 7[7] -> 6[6] via P2P/CUMEM cnode7-008:628130:637920 [7] NCCL INFO Channel 06/0 : 7[7] -> 6[6] via P2P/CUMEM cnode7-008:628130:637920 [7] NCCL INFO Channel 09/0 : 7[7] -> 6[6] via P2P/CUMEM cnode7-008:628130:637920 [7] NCCL INFO Channel 11/0 : 7[7] -> 6[6] via P2P/CUMEM cnode7-008:628130:637920 [7] NCCL INFO Channel 13/0 : 7[7] -> 6[6] via P2P/CUMEM cnode7-008:628130:637920 [7] NCCL INFO Channel 14/0 : 7[7] -> 6[6] via P2P/CUMEM cnode7-008:628124:637498 [1] NCCL INFO Channel 00/0 : 1[1] -> 0[0] via P2P/CUMEM cnode7-008:628124:637498 [1] NCCL INFO Channel 03/0 : 1[1] -> 0[0] via P2P/CUMEM cnode7-008:628124:637498 [1] NCCL INFO Channel 05/0 : 1[1] -> 0[0] via P2P/CUMEM cnode7-008:628124:637498 [1] NCCL INFO Channel 07/0 : 1[1] -> 0[0] via P2P/CUMEM cnode7-008:628124:637498 [1] NCCL INFO Channel 08/0 : 1[1] -> 0[0] via P2P/CUMEM cnode7-008:628124:637498 [1] NCCL INFO Channel 11/0 : 1[1] -> 0[0] via P2P/CUMEM cnode7-008:628124:637498 [1] NCCL INFO Channel 13/0 : 1[1] -> 0[0] via P2P/CUMEM cnode7-008:628124:637498 [1] NCCL INFO Channel 15/0 : 1[1] -> 0[0] via P2P/CUMEM cnode7-008:628125:637915 [2] NCCL INFO Connected all trees cnode7-009:270312:279866 [4] NCCL INFO Connected all trees cnode7-009:270311:279721 [3] NCCL INFO Connected all trees cnode7-009:270310:279373 [2] NCCL INFO Connected all trees cnode7-008:628127:637497 [4] NCCL INFO Connected all trees cnode7-008:628126:637787 [3] NCCL INFO Connected all trees cnode7-009:270313:279722 [5] NCCL INFO Connected all trees cnode7-009:270315:280163 [7] NCCL INFO Connected all trees cnode7-009:270314:279443 [6] NCCL INFO Connected all trees cnode7-008:628128:637782 [5] NCCL INFO Connected all trees cnode7-009:270308:279372 [0] NCCL INFO Connected all trees cnode7-009:270309:280008 [1] NCCL INFO Connected all trees cnode7-008:628130:637920 [7] NCCL INFO Connected all trees cnode7-008:628129:637512 [6] NCCL INFO Connected all trees cnode7-008:628123:637496 [0] NCCL INFO Connected all trees cnode7-008:628124:637498 [1] NCCL INFO Connected all trees cnode7-008:628128:637782 [5] NCCL INFO NVLS comm 0x5555c0f235b0 headRank 5 nHeads 8 buffSize 4194304 memSize 2097152 nvlsPerRankSize 201326592 nvlsTotalSize 1610612736 cnode7-008:628129:637512 [6] NCCL INFO NVLS comm 0x5555c0eeb970 headRank 6 nHeads 8 buffSize 4194304 memSize 2097152 nvlsPerRankSize 201326592 nvlsTotalSize 1610612736 cnode7-008:628126:637787 [3] NCCL INFO NVLS comm 0x5555be768d90 headRank 3 nHeads 8 buffSize 4194304 memSize 2097152 nvlsPerRankSize 201326592 nvlsTotalSize 1610612736 cnode7-009:270314:279443 [6] NCCL INFO NVLS comm 0x5555c0f38de0 headRank 6 nHeads 8 buffSize 4194304 memSize 2097152 nvlsPerRankSize 201326592 nvlsTotalSize 1610612736 cnode7-009:270315:280163 [7] NCCL INFO NVLS comm 0x5555c0eedd70 headRank 7 nHeads 8 buffSize 4194304 memSize 2097152 nvlsPerRankSize 201326592 nvlsTotalSize 1610612736 cnode7-009:270308:279372 [0] NCCL INFO NVLS comm 0x5555b6f4b630 headRank 0 nHeads 8 buffSize 4194304 memSize 2097152 nvlsPerRankSize 201326592 nvlsTotalSize 1610612736 cnode7-009:270311:279721 [3] NCCL INFO NVLS comm 0x5555c0f259a0 headRank 3 nHeads 8 buffSize 4194304 memSize 2097152 nvlsPerRankSize 201326592 nvlsTotalSize 1610612736 cnode7-009:270312:279866 [4] NCCL INFO NVLS comm 0x5555c0f25440 headRank 4 nHeads 8 buffSize 4194304 memSize 2097152 nvlsPerRankSize 201326592 nvlsTotalSize 1610612736 cnode7-009:270309:280008 [1] NCCL INFO NVLS comm 0x5555d4f28520 headRank 1 nHeads 8 buffSize 4194304 memSize 2097152 nvlsPerRankSize 201326592 nvlsTotalSize 1610612736 cnode7-008:628125:637915 [2] NCCL INFO NVLS comm 0x5555c0f2fd80 headRank 2 nHeads 8 buffSize 4194304 memSize 2097152 nvlsPerRankSize 201326592 nvlsTotalSize 1610612736 cnode7-008:628123:637496 [0] NCCL INFO NVLS comm 0x5555b6f0a570 headRank 0 nHeads 8 buffSize 4194304 memSize 2097152 nvlsPerRankSize 201326592 nvlsTotalSize 1610612736 cnode7-008:628127:637497 [4] NCCL INFO NVLS comm 0x5555c0f3bf20 headRank 4 nHeads 8 buffSize 4194304 memSize 2097152 nvlsPerRankSize 201326592 nvlsTotalSize 1610612736 cnode7-008:628130:637920 [7] NCCL INFO NVLS comm 0x5555c0efc560 headRank 7 nHeads 8 buffSize 4194304 memSize 2097152 nvlsPerRankSize 201326592 nvlsTotalSize 1610612736 cnode7-008:628130:637920 [7] NCCL INFO Channel 00/0 : 15[7] -> 7[7] [receive] via NET/IB/8/GDRDMA cnode7-008:628130:637920 [7] NCCL INFO Channel 01/0 : 15[7] -> 7[7] [receive] via NET/IB/8/GDRDMA cnode7-008:628130:637920 [7] NCCL INFO Channel 02/0 : 15[7] -> 7[7] [receive] via NET/IB/8/GDRDMA cnode7-008:628130:637920 [7] NCCL INFO Channel 03/0 : 15[7] -> 7[7] [receive] via NET/IB/8/GDRDMA cnode7-008:628130:637920 [7] NCCL INFO Channel 04/0 : 15[7] -> 7[7] [receive] via NET/IB/8/GDRDMA cnode7-008:628130:637920 [7] NCCL INFO Channel 05/0 : 15[7] -> 7[7] [receive] via NET/IB/8/GDRDMA cnode7-008:628130:637920 [7] NCCL INFO Channel 06/0 : 15[7] -> 7[7] [receive] via NET/IB/8/GDRDMA cnode7-008:628130:637920 [7] NCCL INFO Channel 08/0 : 15[7] -> 7[7] [receive] via NET/IB/8/GDRDMA cnode7-008:628130:637920 [7] NCCL INFO Channel 09/0 : 15[7] -> 7[7] [receive] via NET/IB/8/GDRDMA cnode7-008:628130:637920 [7] NCCL INFO Channel 10/0 : 15[7] -> 7[7] [receive] via NET/IB/8/GDRDMA cnode7-008:628130:637920 [7] NCCL INFO Channel 11/0 : 15[7] -> 7[7] [receive] via NET/IB/8/GDRDMA cnode7-008:628130:637920 [7] NCCL INFO Channel 12/0 : 15[7] -> 7[7] [receive] via NET/IB/8/GDRDMA cnode7-008:628130:637920 [7] NCCL INFO Channel 13/0 : 15[7] -> 7[7] [receive] via NET/IB/8/GDRDMA cnode7-008:628130:637920 [7] NCCL INFO Channel 14/0 : 15[7] -> 7[7] [receive] via NET/IB/8/GDRDMA cnode7-008:628130:637920 [7] NCCL INFO Channel 00/0 : 7[7] -> 15[7] [send] via NET/IB/8/GDRDMA cnode7-008:628130:637920 [7] NCCL INFO Channel 01/0 : 7[7] -> 15[7] [send] via NET/IB/8/GDRDMA cnode7-008:628130:637920 [7] NCCL INFO Channel 02/0 : 7[7] -> 15[7] [send] via NET/IB/8/GDRDMA cnode7-008:628130:637920 [7] NCCL INFO Channel 03/0 : 7[7] -> 15[7] [send] via NET/IB/8/GDRDMA cnode7-008:628130:637920 [7] NCCL INFO Channel 04/0 : 7[7] -> 15[7] [send] via NET/IB/8/GDRDMA cnode7-008:628130:637920 [7] NCCL INFO Channel 05/0 : 7[7] -> 15[7] [send] via NET/IB/8/GDRDMA cnode7-008:628130:637920 [7] NCCL INFO Channel 08/0 : 7[7] -> 15[7] [send] via NET/IB/8/GDRDMA cnode7-008:628130:637920 [7] NCCL INFO Channel 09/0 : 7[7] -> 15[7] [send] via NET/IB/8/GDRDMA cnode7-008:628130:637920 [7] NCCL INFO Channel 10/0 : 7[7] -> 15[7] [send] via NET/IB/8/GDRDMA cnode7-008:628130:637920 [7] NCCL INFO Channel 11/0 : 7[7] -> 15[7] [send] via NET/IB/8/GDRDMA cnode7-008:628130:637920 [7] NCCL INFO Channel 12/0 : 7[7] -> 15[7] [send] via NET/IB/8/GDRDMA cnode7-008:628130:637920 [7] NCCL INFO Channel 13/0 : 7[7] -> 15[7] [send] via NET/IB/8/GDRDMA cnode7-008:628124:637498 [1] NCCL INFO NVLS comm 0x5555c0f0dbb0 headRank 1 nHeads 8 buffSize 4194304 memSize 2097152 nvlsPerRankSize 201326592 nvlsTotalSize 1610612736 cnode7-008:628124:637498 [1] NCCL INFO Channel 00/0 : 9[1] -> 1[1] [receive] via NET/IB/1/GDRDMA cnode7-008:628124:637498 [1] NCCL INFO Channel 02/0 : 9[1] -> 1[1] [receive] via NET/IB/1/GDRDMA cnode7-008:628124:637498 [1] NCCL INFO Channel 03/0 : 9[1] -> 1[1] [receive] via NET/IB/1/GDRDMA cnode7-008:628124:637498 [1] NCCL INFO Channel 04/0 : 9[1] -> 1[1] [receive] via NET/IB/1/GDRDMA cnode7-008:628124:637498 [1] NCCL INFO Channel 05/0 : 9[1] -> 1[1] [receive] via NET/IB/1/GDRDMA cnode7-008:628124:637498 [1] NCCL INFO Channel 06/0 : 9[1] -> 1[1] [receive] via NET/IB/1/GDRDMA cnode7-008:628124:637498 [1] NCCL INFO Channel 07/0 : 9[1] -> 1[1] [receive] via NET/IB/1/GDRDMA cnode7-008:628124:637498 [1] NCCL INFO Channel 08/0 : 9[1] -> 1[1] [receive] via NET/IB/1/GDRDMA cnode7-008:628124:637498 [1] NCCL INFO Channel 10/0 : 9[1] -> 1[1] [receive] via NET/IB/1/GDRDMA cnode7-008:628124:637498 [1] NCCL INFO Channel 11/0 : 9[1] -> 1[1] [receive] via NET/IB/1/GDRDMA cnode7-008:628124:637498 [1] NCCL INFO Channel 12/0 : 9[1] -> 1[1] [receive] via NET/IB/1/GDRDMA cnode7-008:628124:637498 [1] NCCL INFO Channel 13/0 : 9[1] -> 1[1] [receive] via NET/IB/1/GDRDMA cnode7-008:628124:637498 [1] NCCL INFO Channel 14/0 : 9[1] -> 1[1] [receive] via NET/IB/1/GDRDMA cnode7-008:628124:637498 [1] NCCL INFO Channel 15/0 : 9[1] -> 1[1] [receive] via NET/IB/1/GDRDMA cnode7-008:628124:637498 [1] NCCL INFO Channel 02/0 : 1[1] -> 9[1] [send] via NET/IB/1/GDRDMA cnode7-008:628124:637498 [1] NCCL INFO Channel 03/0 : 1[1] -> 9[1] [send] via NET/IB/1/GDRDMA cnode7-008:628124:637498 [1] NCCL INFO Channel 04/0 : 1[1] -> 9[1] [send] via NET/IB/1/GDRDMA cnode7-008:628124:637498 [1] NCCL INFO Channel 05/0 : 1[1] -> 9[1] [send] via NET/IB/1/GDRDMA cnode7-008:628124:637498 [1] NCCL INFO Channel 06/0 : 1[1] -> 9[1] [send] via NET/IB/1/GDRDMA cnode7-008:628124:637498 [1] NCCL INFO Channel 07/0 : 1[1] -> 9[1] [send] via NET/IB/1/GDRDMA cnode7-008:628124:637498 [1] NCCL INFO Channel 10/0 : 1[1] -> 9[1] [send] via NET/IB/1/GDRDMA cnode7-008:628124:637498 [1] NCCL INFO Channel 11/0 : 1[1] -> 9[1] [send] via NET/IB/1/GDRDMA cnode7-008:628124:637498 [1] NCCL INFO Channel 12/0 : 1[1] -> 9[1] [send] via NET/IB/1/GDRDMA cnode7-008:628124:637498 [1] NCCL INFO Channel 13/0 : 1[1] -> 9[1] [send] via NET/IB/1/GDRDMA cnode7-008:628124:637498 [1] NCCL INFO Channel 14/0 : 1[1] -> 9[1] [send] via NET/IB/1/GDRDMA cnode7-008:628124:637498 [1] NCCL INFO Channel 15/0 : 1[1] -> 9[1] [send] via NET/IB/1/GDRDMA cnode7-009:270310:279373 [2] NCCL INFO NVLS comm 0x5555c0f31ff0 headRank 2 nHeads 8 buffSize 4194304 memSize 2097152 nvlsPerRankSize 201326592 nvlsTotalSize 1610612736 cnode7-009:270313:279722 [5] NCCL INFO NVLS comm 0x5555c0f35c90 headRank 5 nHeads 8 buffSize 4194304 memSize 2097152 nvlsPerRankSize 201326592 nvlsTotalSize 1610612736 cnode7-008:628128:637782 [5] NCCL INFO Channel 00/0 : 13[5] -> 5[5] [receive] via NET/IB/6/GDRDMA cnode7-008:628128:637782 [5] NCCL INFO Channel 01/0 : 13[5] -> 5[5] [receive] via NET/IB/6/GDRDMA cnode7-008:628128:637782 [5] NCCL INFO Channel 02/0 : 13[5] -> 5[5] [receive] via NET/IB/6/GDRDMA cnode7-008:628128:637782 [5] NCCL INFO Channel 03/0 : 13[5] -> 5[5] [receive] via NET/IB/6/GDRDMA cnode7-008:628128:637782 [5] NCCL INFO Channel 04/0 : 13[5] -> 5[5] [receive] via NET/IB/6/GDRDMA cnode7-008:628128:637782 [5] NCCL INFO Channel 06/0 : 13[5] -> 5[5] [receive] via NET/IB/6/GDRDMA cnode7-008:628128:637782 [5] NCCL INFO Channel 07/0 : 13[5] -> 5[5] [receive] via NET/IB/6/GDRDMA cnode7-008:628128:637782 [5] NCCL INFO Channel 08/0 : 13[5] -> 5[5] [receive] via NET/IB/6/GDRDMA cnode7-008:628128:637782 [5] NCCL INFO Channel 09/0 : 13[5] -> 5[5] [receive] via NET/IB/6/GDRDMA cnode7-008:628128:637782 [5] NCCL INFO Channel 10/0 : 13[5] -> 5[5] [receive] via NET/IB/6/GDRDMA cnode7-008:628128:637782 [5] NCCL INFO Channel 11/0 : 13[5] -> 5[5] [receive] via NET/IB/6/GDRDMA cnode7-008:628128:637782 [5] NCCL INFO Channel 12/0 : 13[5] -> 5[5] [receive] via NET/IB/6/GDRDMA cnode7-008:628128:637782 [5] NCCL INFO Channel 14/0 : 13[5] -> 5[5] [receive] via NET/IB/6/GDRDMA cnode7-008:628128:637782 [5] NCCL INFO Channel 15/0 : 13[5] -> 5[5] [receive] via NET/IB/6/GDRDMA cnode7-008:628128:637782 [5] NCCL INFO Channel 00/0 : 5[5] -> 13[5] [send] via NET/IB/6/GDRDMA cnode7-008:628128:637782 [5] NCCL INFO Channel 01/0 : 5[5] -> 13[5] [send] via NET/IB/6/GDRDMA cnode7-008:628128:637782 [5] NCCL INFO Channel 02/0 : 5[5] -> 13[5] [send] via NET/IB/6/GDRDMA cnode7-008:628128:637782 [5] NCCL INFO Channel 03/0 : 5[5] -> 13[5] [send] via NET/IB/6/GDRDMA cnode7-008:628128:637782 [5] NCCL INFO Channel 06/0 : 5[5] -> 13[5] [send] via NET/IB/6/GDRDMA cnode7-008:628128:637782 [5] NCCL INFO Channel 07/0 : 5[5] -> 13[5] [send] via NET/IB/6/GDRDMA cnode7-008:628128:637782 [5] NCCL INFO Channel 08/0 : 5[5] -> 13[5] [send] via NET/IB/6/GDRDMA cnode7-008:628128:637782 [5] NCCL INFO Channel 09/0 : 5[5] -> 13[5] [send] via NET/IB/6/GDRDMA cnode7-008:628128:637782 [5] NCCL INFO Channel 10/0 : 5[5] -> 13[5] [send] via NET/IB/6/GDRDMA cnode7-008:628128:637782 [5] NCCL INFO Channel 11/0 : 5[5] -> 13[5] [send] via NET/IB/6/GDRDMA cnode7-008:628128:637782 [5] NCCL INFO Channel 14/0 : 5[5] -> 13[5] [send] via NET/IB/6/GDRDMA cnode7-008:628128:637782 [5] NCCL INFO Channel 15/0 : 5[5] -> 13[5] [send] via NET/IB/6/GDRDMA cnode7-008:628129:637512 [6] NCCL INFO Channel 00/0 : 14[6] -> 6[6] [receive] via NET/IB/7/GDRDMA cnode7-008:628129:637512 [6] NCCL INFO Channel 01/0 : 14[6] -> 6[6] [receive] via NET/IB/7/GDRDMA cnode7-008:628129:637512 [6] NCCL INFO Channel 02/0 : 14[6] -> 6[6] [receive] via NET/IB/7/GDRDMA cnode7-008:628129:637512 [6] NCCL INFO Channel 03/0 : 14[6] -> 6[6] [receive] via NET/IB/7/GDRDMA cnode7-008:628129:637512 [6] NCCL INFO Channel 04/0 : 14[6] -> 6[6] [receive] via NET/IB/7/GDRDMA cnode7-008:628129:637512 [6] NCCL INFO Channel 05/0 : 14[6] -> 6[6] [receive] via NET/IB/7/GDRDMA cnode7-008:628129:637512 [6] NCCL INFO Channel 07/0 : 14[6] -> 6[6] [receive] via NET/IB/7/GDRDMA cnode7-008:628129:637512 [6] NCCL INFO Channel 08/0 : 14[6] -> 6[6] [receive] via NET/IB/7/GDRDMA cnode7-008:628129:637512 [6] NCCL INFO Channel 09/0 : 14[6] -> 6[6] [receive] via NET/IB/7/GDRDMA cnode7-008:628129:637512 [6] NCCL INFO Channel 10/0 : 14[6] -> 6[6] [receive] via NET/IB/7/GDRDMA cnode7-008:628129:637512 [6] NCCL INFO Channel 11/0 : 14[6] -> 6[6] [receive] via NET/IB/7/GDRDMA cnode7-008:628129:637512 [6] NCCL INFO Channel 12/0 : 14[6] -> 6[6] [receive] via NET/IB/7/GDRDMA cnode7-008:628129:637512 [6] NCCL INFO Channel 13/0 : 14[6] -> 6[6] [receive] via NET/IB/7/GDRDMA cnode7-008:628129:637512 [6] NCCL INFO Channel 15/0 : 14[6] -> 6[6] [receive] via NET/IB/7/GDRDMA cnode7-008:628129:637512 [6] NCCL INFO Channel 00/0 : 6[6] -> 14[6] [send] via NET/IB/7/GDRDMA cnode7-008:628129:637512 [6] NCCL INFO Channel 01/0 : 6[6] -> 14[6] [send] via NET/IB/7/GDRDMA cnode7-008:628129:637512 [6] NCCL INFO Channel 02/0 : 6[6] -> 14[6] [send] via NET/IB/7/GDRDMA cnode7-008:628129:637512 [6] NCCL INFO Channel 03/0 : 6[6] -> 14[6] [send] via NET/IB/7/GDRDMA cnode7-008:628129:637512 [6] NCCL INFO Channel 04/0 : 6[6] -> 14[6] [send] via NET/IB/7/GDRDMA cnode7-008:628129:637512 [6] NCCL INFO Channel 05/0 : 6[6] -> 14[6] [send] via NET/IB/7/GDRDMA cnode7-008:628129:637512 [6] NCCL INFO Channel 08/0 : 6[6] -> 14[6] [send] via NET/IB/7/GDRDMA cnode7-008:628129:637512 [6] NCCL INFO Channel 09/0 : 6[6] -> 14[6] [send] via NET/IB/7/GDRDMA cnode7-008:628129:637512 [6] NCCL INFO Channel 10/0 : 6[6] -> 14[6] [send] via NET/IB/7/GDRDMA cnode7-008:628129:637512 [6] NCCL INFO Channel 11/0 : 6[6] -> 14[6] [send] via NET/IB/7/GDRDMA cnode7-008:628129:637512 [6] NCCL INFO Channel 12/0 : 6[6] -> 14[6] [send] via NET/IB/7/GDRDMA cnode7-008:628129:637512 [6] NCCL INFO Channel 13/0 : 6[6] -> 14[6] [send] via NET/IB/7/GDRDMA cnode7-008:628126:637787 [3] NCCL INFO Channel 00/0 : 11[3] -> 3[3] [receive] via NET/IB/3/GDRDMA cnode7-008:628126:637787 [3] NCCL INFO Channel 01/0 : 11[3] -> 3[3] [receive] via NET/IB/3/GDRDMA cnode7-008:628126:637787 [3] NCCL INFO Channel 02/0 : 11[3] -> 3[3] [receive] via NET/IB/3/GDRDMA cnode7-008:628126:637787 [3] NCCL INFO Channel 04/0 : 11[3] -> 3[3] [receive] via NET/IB/3/GDRDMA cnode7-008:628126:637787 [3] NCCL INFO Channel 05/0 : 11[3] -> 3[3] [receive] via NET/IB/3/GDRDMA cnode7-008:628126:637787 [3] NCCL INFO Channel 06/0 : 11[3] -> 3[3] [receive] via NET/IB/3/GDRDMA cnode7-008:628126:637787 [3] NCCL INFO Channel 07/0 : 11[3] -> 3[3] [receive] via NET/IB/3/GDRDMA cnode7-008:628126:637787 [3] NCCL INFO Channel 08/0 : 11[3] -> 3[3] [receive] via NET/IB/3/GDRDMA cnode7-008:628126:637787 [3] NCCL INFO Channel 09/0 : 11[3] -> 3[3] [receive] via NET/IB/3/GDRDMA cnode7-008:628126:637787 [3] NCCL INFO Channel 10/0 : 11[3] -> 3[3] [receive] via NET/IB/3/GDRDMA cnode7-008:628126:637787 [3] NCCL INFO Channel 12/0 : 11[3] -> 3[3] [receive] via NET/IB/3/GDRDMA cnode7-008:628126:637787 [3] NCCL INFO Channel 13/0 : 11[3] -> 3[3] [receive] via NET/IB/3/GDRDMA cnode7-008:628126:637787 [3] NCCL INFO Channel 14/0 : 11[3] -> 3[3] [receive] via NET/IB/3/GDRDMA cnode7-008:628126:637787 [3] NCCL INFO Channel 15/0 : 11[3] -> 3[3] [receive] via NET/IB/3/GDRDMA cnode7-008:628126:637787 [3] NCCL INFO Channel 00/0 : 3[3] -> 11[3] [send] via NET/IB/3/GDRDMA cnode7-008:628126:637787 [3] NCCL INFO Channel 01/0 : 3[3] -> 11[3] [send] via NET/IB/3/GDRDMA cnode7-008:628126:637787 [3] NCCL INFO Channel 04/0 : 3[3] -> 11[3] [send] via NET/IB/3/GDRDMA cnode7-008:628126:637787 [3] NCCL INFO Channel 05/0 : 3[3] -> 11[3] [send] via NET/IB/3/GDRDMA cnode7-008:628126:637787 [3] NCCL INFO Channel 06/0 : 3[3] -> 11[3] [send] via NET/IB/3/GDRDMA cnode7-008:628126:637787 [3] NCCL INFO Channel 07/0 : 3[3] -> 11[3] [send] via NET/IB/3/GDRDMA cnode7-008:628126:637787 [3] NCCL INFO Channel 08/0 : 3[3] -> 11[3] [send] via NET/IB/3/GDRDMA cnode7-008:628126:637787 [3] NCCL INFO Channel 09/0 : 3[3] -> 11[3] [send] via NET/IB/3/GDRDMA cnode7-008:628126:637787 [3] NCCL INFO Channel 12/0 : 3[3] -> 11[3] [send] via NET/IB/3/GDRDMA cnode7-008:628126:637787 [3] NCCL INFO Channel 13/0 : 3[3] -> 11[3] [send] via NET/IB/3/GDRDMA cnode7-008:628126:637787 [3] NCCL INFO Channel 14/0 : 3[3] -> 11[3] [send] via NET/IB/3/GDRDMA cnode7-008:628126:637787 [3] NCCL INFO Channel 15/0 : 3[3] -> 11[3] [send] via NET/IB/3/GDRDMA cnode7-009:270314:279443 [6] NCCL INFO Channel 00/0 : 6[6] -> 14[6] [receive] via NET/IB/7/GDRDMA cnode7-009:270314:279443 [6] NCCL INFO Channel 01/0 : 6[6] -> 14[6] [receive] via NET/IB/7/GDRDMA cnode7-009:270314:279443 [6] NCCL INFO Channel 02/0 : 6[6] -> 14[6] [receive] via NET/IB/7/GDRDMA cnode7-009:270314:279443 [6] NCCL INFO Channel 03/0 : 6[6] -> 14[6] [receive] via NET/IB/7/GDRDMA cnode7-009:270314:279443 [6] NCCL INFO Channel 04/0 : 6[6] -> 14[6] [receive] via NET/IB/7/GDRDMA cnode7-009:270314:279443 [6] NCCL INFO Channel 05/0 : 6[6] -> 14[6] [receive] via NET/IB/7/GDRDMA cnode7-009:270314:279443 [6] NCCL INFO Channel 08/0 : 6[6] -> 14[6] [receive] via NET/IB/7/GDRDMA cnode7-009:270314:279443 [6] NCCL INFO Channel 09/0 : 6[6] -> 14[6] [receive] via NET/IB/7/GDRDMA cnode7-009:270314:279443 [6] NCCL INFO Channel 10/0 : 6[6] -> 14[6] [receive] via NET/IB/7/GDRDMA cnode7-009:270314:279443 [6] NCCL INFO Channel 11/0 : 6[6] -> 14[6] [receive] via NET/IB/7/GDRDMA cnode7-009:270314:279443 [6] NCCL INFO Channel 12/0 : 6[6] -> 14[6] [receive] via NET/IB/7/GDRDMA cnode7-009:270314:279443 [6] NCCL INFO Channel 13/0 : 6[6] -> 14[6] [receive] via NET/IB/7/GDRDMA cnode7-009:270314:279443 [6] NCCL INFO Channel 00/0 : 14[6] -> 6[6] [send] via NET/IB/7/GDRDMA cnode7-009:270314:279443 [6] NCCL INFO Channel 01/0 : 14[6] -> 6[6] [send] via NET/IB/7/GDRDMA cnode7-009:270314:279443 [6] NCCL INFO Channel 02/0 : 14[6] -> 6[6] [send] via NET/IB/7/GDRDMA cnode7-009:270314:279443 [6] NCCL INFO Channel 03/0 : 14[6] -> 6[6] [send] via NET/IB/7/GDRDMA cnode7-009:270314:279443 [6] NCCL INFO Channel 04/0 : 14[6] -> 6[6] [send] via NET/IB/7/GDRDMA cnode7-009:270314:279443 [6] NCCL INFO Channel 05/0 : 14[6] -> 6[6] [send] via NET/IB/7/GDRDMA cnode7-009:270314:279443 [6] NCCL INFO Channel 07/0 : 14[6] -> 6[6] [send] via NET/IB/7/GDRDMA cnode7-009:270314:279443 [6] NCCL INFO Channel 08/0 : 14[6] -> 6[6] [send] via NET/IB/7/GDRDMA cnode7-009:270314:279443 [6] NCCL INFO Channel 09/0 : 14[6] -> 6[6] [send] via NET/IB/7/GDRDMA cnode7-009:270314:279443 [6] NCCL INFO Channel 10/0 : 14[6] -> 6[6] [send] via NET/IB/7/GDRDMA cnode7-009:270314:279443 [6] NCCL INFO Channel 11/0 : 14[6] -> 6[6] [send] via NET/IB/7/GDRDMA cnode7-009:270314:279443 [6] NCCL INFO Channel 12/0 : 14[6] -> 6[6] [send] via NET/IB/7/GDRDMA cnode7-009:270314:279443 [6] NCCL INFO Channel 13/0 : 14[6] -> 6[6] [send] via NET/IB/7/GDRDMA cnode7-009:270314:279443 [6] NCCL INFO Channel 15/0 : 14[6] -> 6[6] [send] via NET/IB/7/GDRDMA cnode7-009:270315:280163 [7] NCCL INFO Channel 00/0 : 7[7] -> 15[7] [receive] via NET/IB/8/GDRDMA cnode7-009:270315:280163 [7] NCCL INFO Channel 01/0 : 7[7] -> 15[7] [receive] via NET/IB/8/GDRDMA cnode7-009:270315:280163 [7] NCCL INFO Channel 02/0 : 7[7] -> 15[7] [receive] via NET/IB/8/GDRDMA cnode7-009:270315:280163 [7] NCCL INFO Channel 03/0 : 7[7] -> 15[7] [receive] via NET/IB/8/GDRDMA cnode7-009:270315:280163 [7] NCCL INFO Channel 04/0 : 7[7] -> 15[7] [receive] via NET/IB/8/GDRDMA cnode7-009:270315:280163 [7] NCCL INFO Channel 05/0 : 7[7] -> 15[7] [receive] via NET/IB/8/GDRDMA cnode7-009:270315:280163 [7] NCCL INFO Channel 08/0 : 7[7] -> 15[7] [receive] via NET/IB/8/GDRDMA cnode7-009:270315:280163 [7] NCCL INFO Channel 09/0 : 7[7] -> 15[7] [receive] via NET/IB/8/GDRDMA cnode7-009:270315:280163 [7] NCCL INFO Channel 10/0 : 7[7] -> 15[7] [receive] via NET/IB/8/GDRDMA cnode7-009:270315:280163 [7] NCCL INFO Channel 11/0 : 7[7] -> 15[7] [receive] via NET/IB/8/GDRDMA cnode7-009:270315:280163 [7] NCCL INFO Channel 12/0 : 7[7] -> 15[7] [receive] via NET/IB/8/GDRDMA cnode7-009:270315:280163 [7] NCCL INFO Channel 13/0 : 7[7] -> 15[7] [receive] via NET/IB/8/GDRDMA cnode7-009:270315:280163 [7] NCCL INFO Channel 00/0 : 15[7] -> 7[7] [send] via NET/IB/8/GDRDMA cnode7-009:270315:280163 [7] NCCL INFO Channel 01/0 : 15[7] -> 7[7] [send] via NET/IB/8/GDRDMA cnode7-009:270315:280163 [7] NCCL INFO Channel 02/0 : 15[7] -> 7[7] [send] via NET/IB/8/GDRDMA cnode7-009:270315:280163 [7] NCCL INFO Channel 03/0 : 15[7] -> 7[7] [send] via NET/IB/8/GDRDMA cnode7-009:270315:280163 [7] NCCL INFO Channel 04/0 : 15[7] -> 7[7] [send] via NET/IB/8/GDRDMA cnode7-009:270315:280163 [7] NCCL INFO Channel 05/0 : 15[7] -> 7[7] [send] via NET/IB/8/GDRDMA cnode7-009:270315:280163 [7] NCCL INFO Channel 06/0 : 15[7] -> 7[7] [send] via NET/IB/8/GDRDMA cnode7-009:270315:280163 [7] NCCL INFO Channel 08/0 : 15[7] -> 7[7] [send] via NET/IB/8/GDRDMA cnode7-009:270315:280163 [7] NCCL INFO Channel 09/0 : 15[7] -> 7[7] [send] via NET/IB/8/GDRDMA cnode7-009:270315:280163 [7] NCCL INFO Channel 10/0 : 15[7] -> 7[7] [send] via NET/IB/8/GDRDMA cnode7-009:270315:280163 [7] NCCL INFO Channel 11/0 : 15[7] -> 7[7] [send] via NET/IB/8/GDRDMA cnode7-009:270315:280163 [7] NCCL INFO Channel 12/0 : 15[7] -> 7[7] [send] via NET/IB/8/GDRDMA cnode7-009:270315:280163 [7] NCCL INFO Channel 13/0 : 15[7] -> 7[7] [send] via NET/IB/8/GDRDMA cnode7-009:270315:280163 [7] NCCL INFO Channel 14/0 : 15[7] -> 7[7] [send] via NET/IB/8/GDRDMA cnode7-009:270308:279372 [0] NCCL INFO Channel 02/0 : 0[0] -> 8[0] [receive] via NET/IB/0/GDRDMA cnode7-009:270308:279372 [0] NCCL INFO Channel 03/0 : 0[0] -> 8[0] [receive] via NET/IB/0/GDRDMA cnode7-009:270308:279372 [0] NCCL INFO Channel 04/0 : 0[0] -> 8[0] [receive] via NET/IB/0/GDRDMA cnode7-009:270308:279372 [0] NCCL INFO Channel 05/0 : 0[0] -> 8[0] [receive] via NET/IB/0/GDRDMA cnode7-009:270308:279372 [0] NCCL INFO Channel 06/0 : 0[0] -> 8[0] [receive] via NET/IB/0/GDRDMA cnode7-009:270308:279372 [0] NCCL INFO Channel 07/0 : 0[0] -> 8[0] [receive] via NET/IB/0/GDRDMA cnode7-009:270308:279372 [0] NCCL INFO Channel 10/0 : 0[0] -> 8[0] [receive] via NET/IB/0/GDRDMA cnode7-009:270308:279372 [0] NCCL INFO Channel 11/0 : 0[0] -> 8[0] [receive] via NET/IB/0/GDRDMA cnode7-009:270308:279372 [0] NCCL INFO Channel 12/0 : 0[0] -> 8[0] [receive] via NET/IB/0/GDRDMA cnode7-009:270308:279372 [0] NCCL INFO Channel 13/0 : 0[0] -> 8[0] [receive] via NET/IB/0/GDRDMA cnode7-009:270308:279372 [0] NCCL INFO Channel 14/0 : 0[0] -> 8[0] [receive] via NET/IB/0/GDRDMA cnode7-009:270308:279372 [0] NCCL INFO Channel 15/0 : 0[0] -> 8[0] [receive] via NET/IB/0/GDRDMA cnode7-009:270308:279372 [0] NCCL INFO Channel 01/0 : 8[0] -> 0[0] [send] via NET/IB/0/GDRDMA cnode7-009:270308:279372 [0] NCCL INFO Channel 02/0 : 8[0] -> 0[0] [send] via NET/IB/0/GDRDMA cnode7-009:270308:279372 [0] NCCL INFO Channel 03/0 : 8[0] -> 0[0] [send] via NET/IB/0/GDRDMA cnode7-009:270308:279372 [0] NCCL INFO Channel 04/0 : 8[0] -> 0[0] [send] via NET/IB/0/GDRDMA cnode7-009:270308:279372 [0] NCCL INFO Channel 05/0 : 8[0] -> 0[0] [send] via NET/IB/0/GDRDMA cnode7-009:270308:279372 [0] NCCL INFO Channel 06/0 : 8[0] -> 0[0] [send] via NET/IB/0/GDRDMA cnode7-009:270308:279372 [0] NCCL INFO Channel 07/0 : 8[0] -> 0[0] [send] via NET/IB/0/GDRDMA cnode7-009:270308:279372 [0] NCCL INFO Channel 09/0 : 8[0] -> 0[0] [send] via NET/IB/0/GDRDMA cnode7-009:270308:279372 [0] NCCL INFO Channel 10/0 : 8[0] -> 0[0] [send] via NET/IB/0/GDRDMA cnode7-009:270308:279372 [0] NCCL INFO Channel 11/0 : 8[0] -> 0[0] [send] via NET/IB/0/GDRDMA cnode7-009:270308:279372 [0] NCCL INFO Channel 12/0 : 8[0] -> 0[0] [send] via NET/IB/0/GDRDMA cnode7-009:270308:279372 [0] NCCL INFO Channel 13/0 : 8[0] -> 0[0] [send] via NET/IB/0/GDRDMA cnode7-009:270308:279372 [0] NCCL INFO Channel 14/0 : 8[0] -> 0[0] [send] via NET/IB/0/GDRDMA cnode7-009:270308:279372 [0] NCCL INFO Channel 15/0 : 8[0] -> 0[0] [send] via NET/IB/0/GDRDMA cnode7-009:270311:279721 [3] NCCL INFO Channel 00/0 : 3[3] -> 11[3] [receive] via NET/IB/3/GDRDMA cnode7-009:270311:279721 [3] NCCL INFO Channel 01/0 : 3[3] -> 11[3] [receive] via NET/IB/3/GDRDMA cnode7-009:270311:279721 [3] NCCL INFO Channel 04/0 : 3[3] -> 11[3] [receive] via NET/IB/3/GDRDMA cnode7-009:270311:279721 [3] NCCL INFO Channel 05/0 : 3[3] -> 11[3] [receive] via NET/IB/3/GDRDMA cnode7-009:270311:279721 [3] NCCL INFO Channel 06/0 : 3[3] -> 11[3] [receive] via NET/IB/3/GDRDMA cnode7-009:270311:279721 [3] NCCL INFO Channel 07/0 : 3[3] -> 11[3] [receive] via NET/IB/3/GDRDMA cnode7-009:270311:279721 [3] NCCL INFO Channel 08/0 : 3[3] -> 11[3] [receive] via NET/IB/3/GDRDMA cnode7-009:270311:279721 [3] NCCL INFO Channel 09/0 : 3[3] -> 11[3] [receive] via NET/IB/3/GDRDMA cnode7-009:270311:279721 [3] NCCL INFO Channel 12/0 : 3[3] -> 11[3] [receive] via NET/IB/3/GDRDMA cnode7-009:270311:279721 [3] NCCL INFO Channel 13/0 : 3[3] -> 11[3] [receive] via NET/IB/3/GDRDMA cnode7-009:270311:279721 [3] NCCL INFO Channel 14/0 : 3[3] -> 11[3] [receive] via NET/IB/3/GDRDMA cnode7-009:270311:279721 [3] NCCL INFO Channel 15/0 : 3[3] -> 11[3] [receive] via NET/IB/3/GDRDMA cnode7-009:270311:279721 [3] NCCL INFO Channel 00/0 : 11[3] -> 3[3] [send] via NET/IB/3/GDRDMA cnode7-009:270311:279721 [3] NCCL INFO Channel 01/0 : 11[3] -> 3[3] [send] via NET/IB/3/GDRDMA cnode7-009:270311:279721 [3] NCCL INFO Channel 02/0 : 11[3] -> 3[3] [send] via NET/IB/3/GDRDMA cnode7-009:270311:279721 [3] NCCL INFO Channel 04/0 : 11[3] -> 3[3] [send] via NET/IB/3/GDRDMA cnode7-009:270311:279721 [3] NCCL INFO Channel 05/0 : 11[3] -> 3[3] [send] via NET/IB/3/GDRDMA cnode7-009:270311:279721 [3] NCCL INFO Channel 06/0 : 11[3] -> 3[3] [send] via NET/IB/3/GDRDMA cnode7-009:270311:279721 [3] NCCL INFO Channel 07/0 : 11[3] -> 3[3] [send] via NET/IB/3/GDRDMA cnode7-009:270311:279721 [3] NCCL INFO Channel 08/0 : 11[3] -> 3[3] [send] via NET/IB/3/GDRDMA cnode7-009:270311:279721 [3] NCCL INFO Channel 09/0 : 11[3] -> 3[3] [send] via NET/IB/3/GDRDMA cnode7-009:270311:279721 [3] NCCL INFO Channel 10/0 : 11[3] -> 3[3] [send] via NET/IB/3/GDRDMA cnode7-009:270311:279721 [3] NCCL INFO Channel 12/0 : 11[3] -> 3[3] [send] via NET/IB/3/GDRDMA cnode7-009:270311:279721 [3] NCCL INFO Channel 13/0 : 11[3] -> 3[3] [send] via NET/IB/3/GDRDMA cnode7-009:270311:279721 [3] NCCL INFO Channel 14/0 : 11[3] -> 3[3] [send] via NET/IB/3/GDRDMA cnode7-009:270311:279721 [3] NCCL INFO Channel 15/0 : 11[3] -> 3[3] [send] via NET/IB/3/GDRDMA cnode7-009:270312:279866 [4] NCCL INFO Channel 00/0 : 4[4] -> 12[4] [receive] via NET/IB/4/GDRDMA cnode7-009:270312:279866 [4] NCCL INFO Channel 01/0 : 4[4] -> 12[4] [receive] via NET/IB/4/GDRDMA cnode7-009:270312:279866 [4] NCCL INFO Channel 02/0 : 4[4] -> 12[4] [receive] via NET/IB/4/GDRDMA cnode7-009:270312:279866 [4] NCCL INFO Channel 03/0 : 4[4] -> 12[4] [receive] via NET/IB/4/GDRDMA cnode7-009:270312:279866 [4] NCCL INFO Channel 06/0 : 4[4] -> 12[4] [receive] via NET/IB/4/GDRDMA cnode7-009:270312:279866 [4] NCCL INFO Channel 07/0 : 4[4] -> 12[4] [receive] via NET/IB/4/GDRDMA cnode7-009:270312:279866 [4] NCCL INFO Channel 08/0 : 4[4] -> 12[4] [receive] via NET/IB/4/GDRDMA cnode7-009:270312:279866 [4] NCCL INFO Channel 09/0 : 4[4] -> 12[4] [receive] via NET/IB/4/GDRDMA cnode7-009:270312:279866 [4] NCCL INFO Channel 10/0 : 4[4] -> 12[4] [receive] via NET/IB/4/GDRDMA cnode7-009:270312:279866 [4] NCCL INFO Channel 11/0 : 4[4] -> 12[4] [receive] via NET/IB/4/GDRDMA cnode7-009:270312:279866 [4] NCCL INFO Channel 14/0 : 4[4] -> 12[4] [receive] via NET/IB/4/GDRDMA cnode7-009:270312:279866 [4] NCCL INFO Channel 15/0 : 4[4] -> 12[4] [receive] via NET/IB/4/GDRDMA cnode7-009:270312:279866 [4] NCCL INFO Channel 00/0 : 12[4] -> 4[4] [send] via NET/IB/4/GDRDMA cnode7-009:270312:279866 [4] NCCL INFO Channel 01/0 : 12[4] -> 4[4] [send] via NET/IB/4/GDRDMA cnode7-009:270312:279866 [4] NCCL INFO Channel 02/0 : 12[4] -> 4[4] [send] via NET/IB/4/GDRDMA cnode7-009:270312:279866 [4] NCCL INFO Channel 03/0 : 12[4] -> 4[4] [send] via NET/IB/4/GDRDMA cnode7-009:270312:279866 [4] NCCL INFO Channel 05/0 : 12[4] -> 4[4] [send] via NET/IB/4/GDRDMA cnode7-009:270312:279866 [4] NCCL INFO Channel 06/0 : 12[4] -> 4[4] [send] via NET/IB/4/GDRDMA cnode7-009:270312:279866 [4] NCCL INFO Channel 07/0 : 12[4] -> 4[4] [send] via NET/IB/4/GDRDMA cnode7-009:270312:279866 [4] NCCL INFO Channel 08/0 : 12[4] -> 4[4] [send] via NET/IB/4/GDRDMA cnode7-009:270312:279866 [4] NCCL INFO Channel 09/0 : 12[4] -> 4[4] [send] via NET/IB/4/GDRDMA cnode7-009:270312:279866 [4] NCCL INFO Channel 10/0 : 12[4] -> 4[4] [send] via NET/IB/4/GDRDMA cnode7-009:270312:279866 [4] NCCL INFO Channel 11/0 : 12[4] -> 4[4] [send] via NET/IB/4/GDRDMA cnode7-009:270312:279866 [4] NCCL INFO Channel 13/0 : 12[4] -> 4[4] [send] via NET/IB/4/GDRDMA cnode7-009:270312:279866 [4] NCCL INFO Channel 14/0 : 12[4] -> 4[4] [send] via NET/IB/4/GDRDMA cnode7-009:270312:279866 [4] NCCL INFO Channel 15/0 : 12[4] -> 4[4] [send] via NET/IB/4/GDRDMA cnode7-009:270309:280008 [1] NCCL INFO Channel 02/0 : 1[1] -> 9[1] [receive] via NET/IB/1/GDRDMA cnode7-009:270309:280008 [1] NCCL INFO Channel 03/0 : 1[1] -> 9[1] [receive] via NET/IB/1/GDRDMA cnode7-009:270309:280008 [1] NCCL INFO Channel 04/0 : 1[1] -> 9[1] [receive] via NET/IB/1/GDRDMA cnode7-009:270309:280008 [1] NCCL INFO Channel 05/0 : 1[1] -> 9[1] [receive] via NET/IB/1/GDRDMA cnode7-009:270309:280008 [1] NCCL INFO Channel 06/0 : 1[1] -> 9[1] [receive] via NET/IB/1/GDRDMA cnode7-009:270309:280008 [1] NCCL INFO Channel 07/0 : 1[1] -> 9[1] [receive] via NET/IB/1/GDRDMA cnode7-009:270309:280008 [1] NCCL INFO Channel 10/0 : 1[1] -> 9[1] [receive] via NET/IB/1/GDRDMA cnode7-009:270309:280008 [1] NCCL INFO Channel 11/0 : 1[1] -> 9[1] [receive] via NET/IB/1/GDRDMA cnode7-009:270309:280008 [1] NCCL INFO Channel 12/0 : 1[1] -> 9[1] [receive] via NET/IB/1/GDRDMA cnode7-009:270309:280008 [1] NCCL INFO Channel 13/0 : 1[1] -> 9[1] [receive] via NET/IB/1/GDRDMA cnode7-009:270309:280008 [1] NCCL INFO Channel 14/0 : 1[1] -> 9[1] [receive] via NET/IB/1/GDRDMA cnode7-009:270309:280008 [1] NCCL INFO Channel 15/0 : 1[1] -> 9[1] [receive] via NET/IB/1/GDRDMA cnode7-009:270309:280008 [1] NCCL INFO Channel 00/0 : 9[1] -> 1[1] [send] via NET/IB/1/GDRDMA cnode7-009:270309:280008 [1] NCCL INFO Channel 02/0 : 9[1] -> 1[1] [send] via NET/IB/1/GDRDMA cnode7-009:270309:280008 [1] NCCL INFO Channel 03/0 : 9[1] -> 1[1] [send] via NET/IB/1/GDRDMA cnode7-009:270309:280008 [1] NCCL INFO Channel 04/0 : 9[1] -> 1[1] [send] via NET/IB/1/GDRDMA cnode7-009:270309:280008 [1] NCCL INFO Channel 05/0 : 9[1] -> 1[1] [send] via NET/IB/1/GDRDMA cnode7-009:270309:280008 [1] NCCL INFO Channel 06/0 : 9[1] -> 1[1] [send] via NET/IB/1/GDRDMA cnode7-009:270309:280008 [1] NCCL INFO Channel 07/0 : 9[1] -> 1[1] [send] via NET/IB/1/GDRDMA cnode7-009:270309:280008 [1] NCCL INFO Channel 08/0 : 9[1] -> 1[1] [send] via NET/IB/1/GDRDMA cnode7-009:270309:280008 [1] NCCL INFO Channel 10/0 : 9[1] -> 1[1] [send] via NET/IB/1/GDRDMA cnode7-009:270309:280008 [1] NCCL INFO Channel 11/0 : 9[1] -> 1[1] [send] via NET/IB/1/GDRDMA cnode7-009:270309:280008 [1] NCCL INFO Channel 12/0 : 9[1] -> 1[1] [send] via NET/IB/1/GDRDMA cnode7-009:270309:280008 [1] NCCL INFO Channel 13/0 : 9[1] -> 1[1] [send] via NET/IB/1/GDRDMA cnode7-009:270309:280008 [1] NCCL INFO Channel 14/0 : 9[1] -> 1[1] [send] via NET/IB/1/GDRDMA cnode7-009:270309:280008 [1] NCCL INFO Channel 15/0 : 9[1] -> 1[1] [send] via NET/IB/1/GDRDMA cnode7-008:628125:637915 [2] NCCL INFO Channel 00/0 : 10[2] -> 2[2] [receive] via NET/IB/2/GDRDMA cnode7-008:628125:637915 [2] NCCL INFO Channel 01/0 : 10[2] -> 2[2] [receive] via NET/IB/2/GDRDMA cnode7-008:628125:637915 [2] NCCL INFO Channel 03/0 : 10[2] -> 2[2] [receive] via NET/IB/2/GDRDMA cnode7-008:628125:637915 [2] NCCL INFO Channel 04/0 : 10[2] -> 2[2] [receive] via NET/IB/2/GDRDMA cnode7-008:628125:637915 [2] NCCL INFO Channel 05/0 : 10[2] -> 2[2] [receive] via NET/IB/2/GDRDMA cnode7-008:628125:637915 [2] NCCL INFO Channel 06/0 : 10[2] -> 2[2] [receive] via NET/IB/2/GDRDMA cnode7-008:628125:637915 [2] NCCL INFO Channel 07/0 : 10[2] -> 2[2] [receive] via NET/IB/2/GDRDMA cnode7-008:628125:637915 [2] NCCL INFO Channel 08/0 : 10[2] -> 2[2] [receive] via NET/IB/2/GDRDMA cnode7-008:628125:637915 [2] NCCL INFO Channel 09/0 : 10[2] -> 2[2] [receive] via NET/IB/2/GDRDMA cnode7-008:628125:637915 [2] NCCL INFO Channel 11/0 : 10[2] -> 2[2] [receive] via NET/IB/2/GDRDMA cnode7-008:628125:637915 [2] NCCL INFO Channel 12/0 : 10[2] -> 2[2] [receive] via NET/IB/2/GDRDMA cnode7-008:628125:637915 [2] NCCL INFO Channel 13/0 : 10[2] -> 2[2] [receive] via NET/IB/2/GDRDMA cnode7-008:628125:637915 [2] NCCL INFO Channel 14/0 : 10[2] -> 2[2] [receive] via NET/IB/2/GDRDMA cnode7-008:628125:637915 [2] NCCL INFO Channel 15/0 : 10[2] -> 2[2] [receive] via NET/IB/2/GDRDMA cnode7-008:628125:637915 [2] NCCL INFO Channel 00/0 : 2[2] -> 10[2] [send] via NET/IB/2/GDRDMA cnode7-008:628125:637915 [2] NCCL INFO Channel 01/0 : 2[2] -> 10[2] [send] via NET/IB/2/GDRDMA cnode7-008:628125:637915 [2] NCCL INFO Channel 04/0 : 2[2] -> 10[2] [send] via NET/IB/2/GDRDMA cnode7-008:628125:637915 [2] NCCL INFO Channel 05/0 : 2[2] -> 10[2] [send] via NET/IB/2/GDRDMA cnode7-008:628125:637915 [2] NCCL INFO Channel 06/0 : 2[2] -> 10[2] [send] via NET/IB/2/GDRDMA cnode7-008:628125:637915 [2] NCCL INFO Channel 07/0 : 2[2] -> 10[2] [send] via NET/IB/2/GDRDMA cnode7-008:628125:637915 [2] NCCL INFO Channel 08/0 : 2[2] -> 10[2] [send] via NET/IB/2/GDRDMA cnode7-008:628125:637915 [2] NCCL INFO Channel 09/0 : 2[2] -> 10[2] [send] via NET/IB/2/GDRDMA cnode7-008:628125:637915 [2] NCCL INFO Channel 12/0 : 2[2] -> 10[2] [send] via NET/IB/2/GDRDMA cnode7-008:628125:637915 [2] NCCL INFO Channel 13/0 : 2[2] -> 10[2] [send] via NET/IB/2/GDRDMA cnode7-008:628125:637915 [2] NCCL INFO Channel 14/0 : 2[2] -> 10[2] [send] via NET/IB/2/GDRDMA cnode7-008:628125:637915 [2] NCCL INFO Channel 15/0 : 2[2] -> 10[2] [send] via NET/IB/2/GDRDMA cnode7-008:628123:637496 [0] NCCL INFO Channel 01/0 : 8[0] -> 0[0] [receive] via NET/IB/0/GDRDMA cnode7-008:628123:637496 [0] NCCL INFO Channel 02/0 : 8[0] -> 0[0] [receive] via NET/IB/0/GDRDMA cnode7-008:628123:637496 [0] NCCL INFO Channel 03/0 : 8[0] -> 0[0] [receive] via NET/IB/0/GDRDMA cnode7-008:628123:637496 [0] NCCL INFO Channel 04/0 : 8[0] -> 0[0] [receive] via NET/IB/0/GDRDMA cnode7-008:628123:637496 [0] NCCL INFO Channel 05/0 : 8[0] -> 0[0] [receive] via NET/IB/0/GDRDMA cnode7-008:628123:637496 [0] NCCL INFO Channel 06/0 : 8[0] -> 0[0] [receive] via NET/IB/0/GDRDMA cnode7-008:628123:637496 [0] NCCL INFO Channel 07/0 : 8[0] -> 0[0] [receive] via NET/IB/0/GDRDMA cnode7-008:628123:637496 [0] NCCL INFO Channel 09/0 : 8[0] -> 0[0] [receive] via NET/IB/0/GDRDMA cnode7-008:628123:637496 [0] NCCL INFO Channel 10/0 : 8[0] -> 0[0] [receive] via NET/IB/0/GDRDMA cnode7-008:628123:637496 [0] NCCL INFO Channel 11/0 : 8[0] -> 0[0] [receive] via NET/IB/0/GDRDMA cnode7-008:628123:637496 [0] NCCL INFO Channel 12/0 : 8[0] -> 0[0] [receive] via NET/IB/0/GDRDMA cnode7-008:628123:637496 [0] NCCL INFO Channel 13/0 : 8[0] -> 0[0] [receive] via NET/IB/0/GDRDMA cnode7-008:628123:637496 [0] NCCL INFO Channel 14/0 : 8[0] -> 0[0] [receive] via NET/IB/0/GDRDMA cnode7-008:628123:637496 [0] NCCL INFO Channel 15/0 : 8[0] -> 0[0] [receive] via NET/IB/0/GDRDMA cnode7-008:628123:637496 [0] NCCL INFO Channel 02/0 : 0[0] -> 8[0] [send] via NET/IB/0/GDRDMA cnode7-008:628123:637496 [0] NCCL INFO Channel 03/0 : 0[0] -> 8[0] [send] via NET/IB/0/GDRDMA cnode7-008:628123:637496 [0] NCCL INFO Channel 04/0 : 0[0] -> 8[0] [send] via NET/IB/0/GDRDMA cnode7-008:628123:637496 [0] NCCL INFO Channel 05/0 : 0[0] -> 8[0] [send] via NET/IB/0/GDRDMA cnode7-008:628123:637496 [0] NCCL INFO Channel 06/0 : 0[0] -> 8[0] [send] via NET/IB/0/GDRDMA cnode7-008:628123:637496 [0] NCCL INFO Channel 07/0 : 0[0] -> 8[0] [send] via NET/IB/0/GDRDMA cnode7-008:628123:637496 [0] NCCL INFO Channel 10/0 : 0[0] -> 8[0] [send] via NET/IB/0/GDRDMA cnode7-008:628123:637496 [0] NCCL INFO Channel 11/0 : 0[0] -> 8[0] [send] via NET/IB/0/GDRDMA cnode7-008:628123:637496 [0] NCCL INFO Channel 12/0 : 0[0] -> 8[0] [send] via NET/IB/0/GDRDMA cnode7-008:628123:637496 [0] NCCL INFO Channel 13/0 : 0[0] -> 8[0] [send] via NET/IB/0/GDRDMA cnode7-008:628123:637496 [0] NCCL INFO Channel 14/0 : 0[0] -> 8[0] [send] via NET/IB/0/GDRDMA cnode7-008:628123:637496 [0] NCCL INFO Channel 15/0 : 0[0] -> 8[0] [send] via NET/IB/0/GDRDMA cnode7-008:628127:637497 [4] NCCL INFO Channel 00/0 : 12[4] -> 4[4] [receive] via NET/IB/4/GDRDMA cnode7-008:628127:637497 [4] NCCL INFO Channel 01/0 : 12[4] -> 4[4] [receive] via NET/IB/4/GDRDMA cnode7-008:628127:637497 [4] NCCL INFO Channel 02/0 : 12[4] -> 4[4] [receive] via NET/IB/4/GDRDMA cnode7-008:628127:637497 [4] NCCL INFO Channel 03/0 : 12[4] -> 4[4] [receive] via NET/IB/4/GDRDMA cnode7-008:628127:637497 [4] NCCL INFO Channel 05/0 : 12[4] -> 4[4] [receive] via NET/IB/4/GDRDMA cnode7-008:628127:637497 [4] NCCL INFO Channel 06/0 : 12[4] -> 4[4] [receive] via NET/IB/4/GDRDMA cnode7-008:628127:637497 [4] NCCL INFO Channel 07/0 : 12[4] -> 4[4] [receive] via NET/IB/4/GDRDMA cnode7-008:628127:637497 [4] NCCL INFO Channel 08/0 : 12[4] -> 4[4] [receive] via NET/IB/4/GDRDMA cnode7-008:628127:637497 [4] NCCL INFO Channel 09/0 : 12[4] -> 4[4] [receive] via NET/IB/4/GDRDMA cnode7-008:628127:637497 [4] NCCL INFO Channel 10/0 : 12[4] -> 4[4] [receive] via NET/IB/4/GDRDMA cnode7-008:628127:637497 [4] NCCL INFO Channel 11/0 : 12[4] -> 4[4] [receive] via NET/IB/4/GDRDMA cnode7-008:628127:637497 [4] NCCL INFO Channel 13/0 : 12[4] -> 4[4] [receive] via NET/IB/4/GDRDMA cnode7-008:628127:637497 [4] NCCL INFO Channel 14/0 : 12[4] -> 4[4] [receive] via NET/IB/4/GDRDMA cnode7-008:628127:637497 [4] NCCL INFO Channel 15/0 : 12[4] -> 4[4] [receive] via NET/IB/4/GDRDMA cnode7-008:628127:637497 [4] NCCL INFO Channel 00/0 : 4[4] -> 12[4] [send] via NET/IB/4/GDRDMA cnode7-008:628127:637497 [4] NCCL INFO Channel 01/0 : 4[4] -> 12[4] [send] via NET/IB/4/GDRDMA cnode7-008:628127:637497 [4] NCCL INFO Channel 02/0 : 4[4] -> 12[4] [send] via NET/IB/4/GDRDMA cnode7-008:628127:637497 [4] NCCL INFO Channel 03/0 : 4[4] -> 12[4] [send] via NET/IB/4/GDRDMA cnode7-008:628127:637497 [4] NCCL INFO Channel 06/0 : 4[4] -> 12[4] [send] via NET/IB/4/GDRDMA cnode7-008:628127:637497 [4] NCCL INFO Channel 07/0 : 4[4] -> 12[4] [send] via NET/IB/4/GDRDMA cnode7-008:628127:637497 [4] NCCL INFO Channel 08/0 : 4[4] -> 12[4] [send] via NET/IB/4/GDRDMA cnode7-008:628127:637497 [4] NCCL INFO Channel 09/0 : 4[4] -> 12[4] [send] via NET/IB/4/GDRDMA cnode7-008:628127:637497 [4] NCCL INFO Channel 10/0 : 4[4] -> 12[4] [send] via NET/IB/4/GDRDMA cnode7-008:628127:637497 [4] NCCL INFO Channel 11/0 : 4[4] -> 12[4] [send] via NET/IB/4/GDRDMA cnode7-008:628127:637497 [4] NCCL INFO Channel 14/0 : 4[4] -> 12[4] [send] via NET/IB/4/GDRDMA cnode7-008:628127:637497 [4] NCCL INFO Channel 15/0 : 4[4] -> 12[4] [send] via NET/IB/4/GDRDMA cnode7-009:270310:279373 [2] NCCL INFO Channel 00/0 : 2[2] -> 10[2] [receive] via NET/IB/2/GDRDMA cnode7-009:270310:279373 [2] NCCL INFO Channel 01/0 : 2[2] -> 10[2] [receive] via NET/IB/2/GDRDMA cnode7-009:270310:279373 [2] NCCL INFO Channel 04/0 : 2[2] -> 10[2] [receive] via NET/IB/2/GDRDMA cnode7-009:270310:279373 [2] NCCL INFO Channel 05/0 : 2[2] -> 10[2] [receive] via NET/IB/2/GDRDMA cnode7-009:270310:279373 [2] NCCL INFO Channel 06/0 : 2[2] -> 10[2] [receive] via NET/IB/2/GDRDMA cnode7-009:270310:279373 [2] NCCL INFO Channel 07/0 : 2[2] -> 10[2] [receive] via NET/IB/2/GDRDMA cnode7-009:270310:279373 [2] NCCL INFO Channel 08/0 : 2[2] -> 10[2] [receive] via NET/IB/2/GDRDMA cnode7-009:270310:279373 [2] NCCL INFO Channel 09/0 : 2[2] -> 10[2] [receive] via NET/IB/2/GDRDMA cnode7-009:270310:279373 [2] NCCL INFO Channel 12/0 : 2[2] -> 10[2] [receive] via NET/IB/2/GDRDMA cnode7-009:270310:279373 [2] NCCL INFO Channel 13/0 : 2[2] -> 10[2] [receive] via NET/IB/2/GDRDMA cnode7-009:270310:279373 [2] NCCL INFO Channel 14/0 : 2[2] -> 10[2] [receive] via NET/IB/2/GDRDMA cnode7-009:270310:279373 [2] NCCL INFO Channel 15/0 : 2[2] -> 10[2] [receive] via NET/IB/2/GDRDMA cnode7-009:270310:279373 [2] NCCL INFO Channel 00/0 : 10[2] -> 2[2] [send] via NET/IB/2/GDRDMA cnode7-009:270310:279373 [2] NCCL INFO Channel 01/0 : 10[2] -> 2[2] [send] via NET/IB/2/GDRDMA cnode7-009:270310:279373 [2] NCCL INFO Channel 03/0 : 10[2] -> 2[2] [send] via NET/IB/2/GDRDMA cnode7-009:270310:279373 [2] NCCL INFO Channel 04/0 : 10[2] -> 2[2] [send] via NET/IB/2/GDRDMA cnode7-009:270310:279373 [2] NCCL INFO Channel 05/0 : 10[2] -> 2[2] [send] via NET/IB/2/GDRDMA cnode7-009:270310:279373 [2] NCCL INFO Channel 06/0 : 10[2] -> 2[2] [send] via NET/IB/2/GDRDMA cnode7-009:270310:279373 [2] NCCL INFO Channel 07/0 : 10[2] -> 2[2] [send] via NET/IB/2/GDRDMA cnode7-009:270310:279373 [2] NCCL INFO Channel 08/0 : 10[2] -> 2[2] [send] via NET/IB/2/GDRDMA cnode7-009:270310:279373 [2] NCCL INFO Channel 09/0 : 10[2] -> 2[2] [send] via NET/IB/2/GDRDMA cnode7-009:270310:279373 [2] NCCL INFO Channel 11/0 : 10[2] -> 2[2] [send] via NET/IB/2/GDRDMA cnode7-009:270310:279373 [2] NCCL INFO Channel 12/0 : 10[2] -> 2[2] [send] via NET/IB/2/GDRDMA cnode7-009:270310:279373 [2] NCCL INFO Channel 13/0 : 10[2] -> 2[2] [send] via NET/IB/2/GDRDMA cnode7-009:270310:279373 [2] NCCL INFO Channel 14/0 : 10[2] -> 2[2] [send] via NET/IB/2/GDRDMA cnode7-009:270310:279373 [2] NCCL INFO Channel 15/0 : 10[2] -> 2[2] [send] via NET/IB/2/GDRDMA cnode7-009:270313:279722 [5] NCCL INFO Channel 00/0 : 5[5] -> 13[5] [receive] via NET/IB/6/GDRDMA cnode7-009:270313:279722 [5] NCCL INFO Channel 01/0 : 5[5] -> 13[5] [receive] via NET/IB/6/GDRDMA cnode7-009:270313:279722 [5] NCCL INFO Channel 02/0 : 5[5] -> 13[5] [receive] via NET/IB/6/GDRDMA cnode7-009:270313:279722 [5] NCCL INFO Channel 03/0 : 5[5] -> 13[5] [receive] via NET/IB/6/GDRDMA cnode7-009:270313:279722 [5] NCCL INFO Channel 06/0 : 5[5] -> 13[5] [receive] via NET/IB/6/GDRDMA cnode7-009:270313:279722 [5] NCCL INFO Channel 07/0 : 5[5] -> 13[5] [receive] via NET/IB/6/GDRDMA cnode7-009:270313:279722 [5] NCCL INFO Channel 08/0 : 5[5] -> 13[5] [receive] via NET/IB/6/GDRDMA cnode7-009:270313:279722 [5] NCCL INFO Channel 09/0 : 5[5] -> 13[5] [receive] via NET/IB/6/GDRDMA cnode7-009:270313:279722 [5] NCCL INFO Channel 10/0 : 5[5] -> 13[5] [receive] via NET/IB/6/GDRDMA cnode7-009:270313:279722 [5] NCCL INFO Channel 11/0 : 5[5] -> 13[5] [receive] via NET/IB/6/GDRDMA cnode7-009:270313:279722 [5] NCCL INFO Channel 14/0 : 5[5] -> 13[5] [receive] via NET/IB/6/GDRDMA cnode7-009:270313:279722 [5] NCCL INFO Channel 15/0 : 5[5] -> 13[5] [receive] via NET/IB/6/GDRDMA cnode7-009:270313:279722 [5] NCCL INFO Channel 00/0 : 13[5] -> 5[5] [send] via NET/IB/6/GDRDMA cnode7-009:270313:279722 [5] NCCL INFO Channel 01/0 : 13[5] -> 5[5] [send] via NET/IB/6/GDRDMA cnode7-009:270313:279722 [5] NCCL INFO Channel 02/0 : 13[5] -> 5[5] [send] via NET/IB/6/GDRDMA cnode7-009:270313:279722 [5] NCCL INFO Channel 03/0 : 13[5] -> 5[5] [send] via NET/IB/6/GDRDMA cnode7-009:270313:279722 [5] NCCL INFO Channel 04/0 : 13[5] -> 5[5] [send] via NET/IB/6/GDRDMA cnode7-009:270313:279722 [5] NCCL INFO Channel 06/0 : 13[5] -> 5[5] [send] via NET/IB/6/GDRDMA cnode7-009:270313:279722 [5] NCCL INFO Channel 07/0 : 13[5] -> 5[5] [send] via NET/IB/6/GDRDMA cnode7-009:270313:279722 [5] NCCL INFO Channel 08/0 : 13[5] -> 5[5] [send] via NET/IB/6/GDRDMA cnode7-009:270313:279722 [5] NCCL INFO Channel 09/0 : 13[5] -> 5[5] [send] via NET/IB/6/GDRDMA cnode7-009:270313:279722 [5] NCCL INFO Channel 10/0 : 13[5] -> 5[5] [send] via NET/IB/6/GDRDMA cnode7-009:270313:279722 [5] NCCL INFO Channel 11/0 : 13[5] -> 5[5] [send] via NET/IB/6/GDRDMA cnode7-009:270313:279722 [5] NCCL INFO Channel 12/0 : 13[5] -> 5[5] [send] via NET/IB/6/GDRDMA cnode7-009:270313:279722 [5] NCCL INFO Channel 14/0 : 13[5] -> 5[5] [send] via NET/IB/6/GDRDMA cnode7-009:270313:279722 [5] NCCL INFO Channel 15/0 : 13[5] -> 5[5] [send] via NET/IB/6/GDRDMA cnode7-008:628126:637787 [3] NCCL INFO Connected NVLS tree cnode7-008:628126:637787 [3] NCCL INFO threadThresholds 8/8/64 | 128/8/64 | 512 | 512 cnode7-008:628126:637787 [3] NCCL INFO 16 coll channels, 0 collnet channels, 16 nvls channels, 16 p2p channels, 2 p2p channels per peer cnode7-009:270309:280008 [1] NCCL INFO Connected NVLS tree cnode7-009:270309:280008 [1] NCCL INFO threadThresholds 8/8/64 | 128/8/64 | 512 | 512 cnode7-009:270309:280008 [1] NCCL INFO 16 coll channels, 0 collnet channels, 16 nvls channels, 16 p2p channels, 2 p2p channels per peer cnode7-009:270311:279721 [3] NCCL INFO Connected NVLS tree cnode7-009:270311:279721 [3] NCCL INFO threadThresholds 8/8/64 | 128/8/64 | 512 | 512 cnode7-009:270311:279721 [3] NCCL INFO 16 coll channels, 0 collnet channels, 16 nvls channels, 16 p2p channels, 2 p2p channels per peer cnode7-009:270312:279866 [4] NCCL INFO Connected NVLS tree cnode7-009:270312:279866 [4] NCCL INFO threadThresholds 8/8/64 | 128/8/64 | 512 | 512 cnode7-009:270312:279866 [4] NCCL INFO 16 coll channels, 0 collnet channels, 16 nvls channels, 16 p2p channels, 2 p2p channels per peer cnode7-009:270308:279372 [0] NCCL INFO Connected NVLS tree cnode7-009:270308:279372 [0] NCCL INFO threadThresholds 8/8/64 | 128/8/64 | 512 | 512 cnode7-009:270308:279372 [0] NCCL INFO 16 coll channels, 0 collnet channels, 16 nvls channels, 16 p2p channels, 2 p2p channels per peer cnode7-009:270310:279373 [2] NCCL INFO Connected NVLS tree cnode7-009:270310:279373 [2] NCCL INFO threadThresholds 8/8/64 | 128/8/64 | 512 | 512 cnode7-009:270310:279373 [2] NCCL INFO 16 coll channels, 0 collnet channels, 16 nvls channels, 16 p2p channels, 2 p2p channels per peer cnode7-008:628125:637915 [2] NCCL INFO Connected NVLS tree cnode7-008:628125:637915 [2] NCCL INFO threadThresholds 8/8/64 | 128/8/64 | 512 | 512 cnode7-008:628125:637915 [2] NCCL INFO 16 coll channels, 0 collnet channels, 16 nvls channels, 16 p2p channels, 2 p2p channels per peer cnode7-009:270314:279443 [6] NCCL INFO Connected NVLS tree cnode7-009:270314:279443 [6] NCCL INFO threadThresholds 8/8/64 | 128/8/64 | 512 | 512 cnode7-009:270314:279443 [6] NCCL INFO 16 coll channels, 0 collnet channels, 16 nvls channels, 16 p2p channels, 2 p2p channels per peer cnode7-008:628123:637496 [0] NCCL INFO Connected NVLS tree cnode7-008:628123:637496 [0] NCCL INFO threadThresholds 8/8/64 | 128/8/64 | 512 | 512 cnode7-008:628123:637496 [0] NCCL INFO 16 coll channels, 0 collnet channels, 16 nvls channels, 16 p2p channels, 2 p2p channels per peer cnode7-008:628127:637497 [4] NCCL INFO Connected NVLS tree cnode7-008:628127:637497 [4] NCCL INFO threadThresholds 8/8/64 | 128/8/64 | 512 | 512 cnode7-008:628127:637497 [4] NCCL INFO 16 coll channels, 0 collnet channels, 16 nvls channels, 16 p2p channels, 2 p2p channels per peer cnode7-008:628124:637498 [1] NCCL INFO Connected NVLS tree cnode7-008:628124:637498 [1] NCCL INFO threadThresholds 8/8/64 | 128/8/64 | 512 | 512 cnode7-008:628124:637498 [1] NCCL INFO 16 coll channels, 0 collnet channels, 16 nvls channels, 16 p2p channels, 2 p2p channels per peer cnode7-009:270313:279722 [5] NCCL INFO Connected NVLS tree cnode7-009:270313:279722 [5] NCCL INFO threadThresholds 8/8/64 | 128/8/64 | 512 | 512 cnode7-009:270313:279722 [5] NCCL INFO 16 coll channels, 0 collnet channels, 16 nvls channels, 16 p2p channels, 2 p2p channels per peer cnode7-008:628128:637782 [5] NCCL INFO Connected NVLS tree cnode7-008:628128:637782 [5] NCCL INFO threadThresholds 8/8/64 | 128/8/64 | 512 | 512 cnode7-008:628128:637782 [5] NCCL INFO 16 coll channels, 0 collnet channels, 16 nvls channels, 16 p2p channels, 2 p2p channels per peer cnode7-008:628129:637512 [6] NCCL INFO Connected NVLS tree cnode7-008:628129:637512 [6] NCCL INFO threadThresholds 8/8/64 | 128/8/64 | 512 | 512 cnode7-008:628129:637512 [6] NCCL INFO 16 coll channels, 0 collnet channels, 16 nvls channels, 16 p2p channels, 2 p2p channels per peer cnode7-009:270315:280163 [7] NCCL INFO Connected NVLS tree cnode7-009:270315:280163 [7] NCCL INFO threadThresholds 8/8/64 | 128/8/64 | 512 | 512 cnode7-009:270315:280163 [7] NCCL INFO 16 coll channels, 0 collnet channels, 16 nvls channels, 16 p2p channels, 2 p2p channels per peer cnode7-009:270309:280008 [1] NCCL INFO comm 0x5555d4f28520 rank 9 nranks 16 cudaDev 1 nvmlDev 1 busId 43000 commId 0x34e5a2ca30f589ad - Init COMPLETE cnode7-008:628130:637920 [7] NCCL INFO Connected NVLS tree cnode7-008:628130:637920 [7] NCCL INFO threadThresholds 8/8/64 | 128/8/64 | 512 | 512 cnode7-008:628130:637920 [7] NCCL INFO 16 coll channels, 0 collnet channels, 16 nvls channels, 16 p2p channels, 2 p2p channels per peer cnode7-008:628125:637915 [2] NCCL INFO comm 0x5555c0f2fd80 rank 2 nranks 16 cudaDev 2 nvmlDev 2 busId 52000 commId 0x34e5a2ca30f589ad - Init COMPLETE cnode7-008:628123:637496 [0] NCCL INFO comm 0x5555b6f0a570 rank 0 nranks 16 cudaDev 0 nvmlDev 0 busId 1b000 commId 0x34e5a2ca30f589ad - Init COMPLETE cnode7-009:270313:279722 [5] NCCL INFO comm 0x5555c0f35c90 rank 13 nranks 16 cudaDev 5 nvmlDev 5 busId c3000 commId 0x34e5a2ca30f589ad - Init COMPLETE cnode7-009:270314:279443 [6] NCCL INFO comm 0x5555c0f38de0 rank 14 nranks 16 cudaDev 6 nvmlDev 6 busId d1000 commId 0x34e5a2ca30f589ad - Init COMPLETE cnode7-009:270315:280163 [7] NCCL INFO comm 0x5555c0eedd70 rank 15 nranks 16 cudaDev 7 nvmlDev 7 busId df000 commId 0x34e5a2ca30f589ad - Init COMPLETE cnode7-009:270308:279372 [0] NCCL INFO comm 0x5555b6f4b630 rank 8 nranks 16 cudaDev 0 nvmlDev 0 busId 1b000 commId 0x34e5a2ca30f589ad - Init COMPLETE cnode7-009:270312:279866 [4] NCCL INFO comm 0x5555c0f25440 rank 12 nranks 16 cudaDev 4 nvmlDev 4 busId 9d000 commId 0x34e5a2ca30f589ad - Init COMPLETE cnode7-009:270311:279721 [3] NCCL INFO comm 0x5555c0f259a0 rank 11 nranks 16 cudaDev 3 nvmlDev 3 busId 61000 commId 0x34e5a2ca30f589ad - Init COMPLETE cnode7-009:270310:279373 [2] NCCL INFO comm 0x5555c0f31ff0 rank 10 nranks 16 cudaDev 2 nvmlDev 2 busId 52000 commId 0x34e5a2ca30f589ad - Init COMPLETE cnode7-008:628130:637920 [7] NCCL INFO comm 0x5555c0efc560 rank 7 nranks 16 cudaDev 7 nvmlDev 7 busId df000 commId 0x34e5a2ca30f589ad - Init COMPLETE cnode7-008:628128:637782 [5] NCCL INFO comm 0x5555c0f235b0 rank 5 nranks 16 cudaDev 5 nvmlDev 5 busId c3000 commId 0x34e5a2ca30f589ad - Init COMPLETE cnode7-008:628126:637787 [3] NCCL INFO comm 0x5555be768d90 rank 3 nranks 16 cudaDev 3 nvmlDev 3 busId 61000 commId 0x34e5a2ca30f589ad - Init COMPLETE cnode7-008:628124:637498 [1] NCCL INFO comm 0x5555c0f0dbb0 rank 1 nranks 16 cudaDev 1 nvmlDev 1 busId 43000 commId 0x34e5a2ca30f589ad - Init COMPLETE cnode7-008:628129:637512 [6] NCCL INFO comm 0x5555c0eeb970 rank 6 nranks 16 cudaDev 6 nvmlDev 6 busId d1000 commId 0x34e5a2ca30f589ad - Init COMPLETE cnode7-008:628127:637497 [4] NCCL INFO comm 0x5555c0f3bf20 rank 4 nranks 16 cudaDev 4 nvmlDev 4 busId 9d000 commId 0x34e5a2ca30f589ad - Init COMPLETE [cnode7-008:0/16] 2024-12-10 08:45:14,475 (deepspeed_trainer:228) INFO: 41epoch:train:1-100batch: iter_time=2.408, loss_ctc=73.555, loss_att=61.050, acc=0.718, loss=64.813, grad_norm=5.867, loss_scale=1.000, learning_rate=6.324e-05, step_time=0.611 [cnode7-008:0/16] 2024-12-10 08:45:51,487 (deepspeed_trainer:228) INFO: 41epoch:train:101-200batch: iter_time=1.088e-04, loss_ctc=71.831, loss_att=54.074, acc=0.724, loss=59.399, grad_norm=5.881, loss_scale=1.000, learning_rate=6.324e-05, step_time=0.370 [cnode7-008:0/16] 2024-12-10 08:46:27,984 (deepspeed_trainer:228) INFO: 41epoch:train:201-300batch: iter_time=1.114e-04, loss_ctc=78.763, loss_att=61.504, acc=0.709, loss=66.676, grad_norm=7.658, loss_scale=1.000, learning_rate=6.323e-05, step_time=0.365 [cnode7-008:0/16] 2024-12-10 08:47:04,088 (deepspeed_trainer:228) INFO: 41epoch:train:301-400batch: iter_time=1.154e-04, loss_ctc=66.813, loss_att=51.931, acc=0.719, loss=56.413, grad_norm=5.784, loss_scale=1.000, learning_rate=6.323e-05, step_time=0.360 srun: Job step aborted: Waiting up to 32 seconds for job step to finish. slurmstepd: error: *** STEP 6577.0 ON cnode7-008 CANCELLED AT 2024-12-10T08:47:14 ***